{"id":9070,"date":"2026-06-17T15:21:55","date_gmt":"2026-06-17T06:21:55","guid":{"rendered":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/?p=9070"},"modified":"2026-06-17T15:27:45","modified_gmt":"2026-06-17T06:27:45","slug":"%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84","status":"publish","type":"post","link":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/","title":{"rendered":"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2"},"content":{"rendered":"<p><a href=\"https:\/\/colab.research.google.com\/github\/T-QARD\/t-wave\/blob\/main\/notebooks\/QA_RBM\/qa_rbm.ipynb\" target=\"_blank\" rel=\"noopener noreferrer\"><img decoding=\"async\" src=\"https:\/\/colab.research.google.com\/assets\/colab-badge.svg\" alt=\"Open in Colab\"><\/a><\/p>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-white ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title ez-toc-toggle\" style=\"cursor:pointer\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E6%A6%82%E8%A6%81\" >\u6982\u8981<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E6%96%87%E7%8C%AE%E6%83%85%E5%A0%B1\" >\u6587\u732e\u60c5\u5831<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E6%BA%96%E5%82%99\" >\u6e96\u5099<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E3%83%A9%E3%82%A4%E3%83%96%E3%83%A9%E3%83%AA%E3%81%AE%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%BC%E3%83%AB%E3%81%A8%E3%82%A4%E3%83%B3%E3%83%9D%E3%83%BC%E3%83%88\" >\u30e9\u30a4\u30d6\u30e9\u30ea\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3068\u30a4\u30f3\u30dd\u30fc\u30c8<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#BAS%E3%83%87%E3%83%BC%E3%82%BF%E3%82%BB%E3%83%83%E3%83%88%E3%81%AE%E6%BA%96%E5%82%99\" >BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u6e96\u5099<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#BAS%E3%83%87%E3%83%BC%E3%82%BF%E3%81%AE%E4%BD%9C%E6%88%90\" >BAS\u30c7\u30fc\u30bf\u306e\u4f5c\u6210<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#BAS%E3%83%87%E3%83%BC%E3%82%BF%E3%81%AE%E7%A2%BA%E8%AA%8D\" >BAS\u30c7\u30fc\u30bf\u306e\u78ba\u8a8d<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#RBM%E3%81%AE%E5%AE%9F%E8%A3%85\" >RBM\u306e\u5b9f\u88c5<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#RBM%E3%81%AE%E5%9F%BA%E6%9C%AC%E3%81%AE%E5%AE%9F%E8%A3%85\" >RBM\u306e\u57fa\u672c\u306e\u5b9f\u88c5<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#CD-1%E3%81%AE%E3%82%B5%E3%83%B3%E3%83%97%E3%83%AA%E3%83%B3%E3%82%B0%E3%81%AB%E3%82%88%E3%82%8BRBM%E3%81%AE%E5%AD%A6%E7%BF%92%E9%96%A2%E6%95%B0%E3%81%AE%E5%AE%9F%E8%A3%85\" >CD-1\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308bRBM\u306e\u5b66\u7fd2\u95a2\u6570\u306e\u5b9f\u88c5<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#SA%E3%81%AE%E3%82%B5%E3%83%B3%E3%83%97%E3%83%AA%E3%83%B3%E3%82%B0%E3%81%AB%E3%82%88%E3%82%8BRBM%E3%81%AE%E5%AD%A6%E7%BF%92%E9%96%A2%E6%95%B0%E3%81%AE%E5%AE%9F%E8%A3%85\" >SA\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308bRBM\u306e\u5b66\u7fd2\u95a2\u6570\u306e\u5b9f\u88c5<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E7%94%BB%E5%83%8F%E5%88%86%E9%A1%9E%E3%81%AE%E6%AD%A3%E8%A7%A3%E7%8E%87%E3%82%92%E3%82%82%E3%81%A8%E3%82%81%E3%82%8B%E9%96%A2%E6%95%B0\" >\u753b\u50cf\u5206\u985e\u306e\u6b63\u89e3\u7387\u3092\u3082\u3068\u3081\u308b\u95a2\u6570<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-13\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%99%E3%82%8B%E9%96%A2%E6%95%B0\" >\u753b\u50cf\u518d\u69cb\u6210\u3059\u308b\u95a2\u6570<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-14\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%AE%E3%82%A8%E3%83%A9%E3%83%BC%E6%95%B0%E3%82%92%E3%82%82%E3%81%A8%E3%82%81%E3%82%8B%E9%96%A2%E6%95%B0\" >\u753b\u50cf\u518d\u69cb\u6210\u306e\u30a8\u30e9\u30fc\u6570\u3092\u3082\u3068\u3081\u308b\u95a2\u6570<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-15\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E5%AF%BE%E6%95%B0%E5%B0%A4%E5%BA%A6%E3%82%92%E3%82%82%E3%81%A8%E3%82%81%E3%82%8B%E9%96%A2%E6%95%B0\" >\u5bfe\u6570\u5c24\u5ea6\u3092\u3082\u3068\u3081\u308b\u95a2\u6570<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-16\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E3%82%AF%E3%83%A9%E3%82%B9%E3%81%AB%E3%82%88%E3%82%8B%E7%B5%B1%E5%90%88\" >\u30af\u30e9\u30b9\u306b\u3088\u308b\u7d71\u5408<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-17\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E5%AE%9F%E9%A8%93\" >\u5b9f\u9a13<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-18\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E3%83%87%E3%83%BC%E3%82%BF%E8%A8%AD%E5%AE%9A\" >\u30c7\u30fc\u30bf\u8a2d\u5b9a<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-19\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E5%AE%9F%E9%A8%931_%E7%94%BB%E5%83%8F%E5%88%86%E9%A1%9E\" >\u5b9f\u9a131 : \u753b\u50cf\u5206\u985e<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-20\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E5%AE%9F%E9%A8%932_%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90\" >\u5b9f\u9a132 \u753b\u50cf\u518d\u69cb\u6210<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-21\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%AE%E7%B5%90%E6%9E%9C\" >\u753b\u50cf\u518d\u69cb\u6210\u306e\u7d50\u679c<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-22\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%AE%E3%82%A8%E3%83%A9%E3%83%BC%E5%88%86%E5%B8%83\" >\u753b\u50cf\u518d\u69cb\u6210\u306e\u30a8\u30e9\u30fc\u5206\u5e03<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-23\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E5%AE%9F%E9%A8%933_%E5%AF%BE%E6%95%B0%E5%B0%A4%E5%BA%A6%E6%AF%94%E8%BC%83\" >\u5b9f\u9a133 \u5bfe\u6570\u5c24\u5ea6\u6bd4\u8f03<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-24\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E3%81%BE%E3%81%A8%E3%82%81\" >\u307e\u3068\u3081<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-25\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#%E3%81%82%E3%81%A8%E3%81%8C%E3%81%8D\" >\u3042\u3068\u304c\u304d<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"%E6%A6%82%E8%A6%81\"><\/span>\u6982\u8981<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u89e3\u8aac\u8a18\u4e8b\u300c<a href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/03\/25\/d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84%e3%83%9e%e3%83%b3%e3%83%9e%e3%82%b7%e3%83%b3\/\">D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2<\/a>\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088\u3073\u5bfe\u6570\u5c24\u5ea6\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3059\u308b\u3068\u3044\u3046\u8ad6\u6587\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5b9f\u969b\u306b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3001\u5143\u8ad6\u6587\u306e\u518d\u73fe\u5b9f\u9a13\u3092\u884c\u3044\u307e\u3059\u3002\u4eca\u56de\u306fQA\u306e\u4ee3\u308f\u308a\u306b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3092\u7528\u3044\u307e\u3057\u305f\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\"><\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h2><span class=\"ez-toc-section\" id=\"%E6%96%87%E7%8C%AE%E6%83%85%E5%A0%B1\"><\/span>\u6587\u732e\u60c5\u5831<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<ul>\n<li>\u30bf\u30a4\u30c8\u30eb : Training Restricted Boltzmann Machines With a D-Wave Quantum Annealer<\/li>\n<li>\u8457\u8005 : Vivek Dixit, Raja Selvarajan, Muhammad A. Alam, Travis S. Humble and Sabre Kais<\/li>\n<li>\u66f8\u8a8c\u60c5\u5831 : <a href=\"https:\/\/doi.org\/10.3389\/fphy.2021.589626\">https:\/\/doi.org\/10.3389\/fphy.2021.589626<\/a><\/li>\n<\/ul>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h2><span class=\"ez-toc-section\" id=\"%E6%BA%96%E5%82%99\"><\/span>\u6e96\u5099<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"%E3%83%A9%E3%82%A4%E3%83%96%E3%83%A9%E3%83%AA%E3%81%AE%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%BC%E3%83%AB%E3%81%A8%E3%82%A4%E3%83%B3%E3%83%9D%E3%83%BC%E3%83%88\"><\/span>\u30e9\u30a4\u30d6\u30e9\u30ea\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3068\u30a4\u30f3\u30dd\u30fc\u30c8<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"err\">!<\/span><span class=\"n\">pip<\/span> <span class=\"n\">install<\/span> <span class=\"n\">openjij<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_subarea output_stream output_stdout output_text\">\n<pre>Collecting openjij\r\n  Downloading openjij-0.11.6-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (8.3 kB)\r\nRequirement already satisfied: numpy&lt;2.4.0,&gt;=1.19.3 in \/usr\/local\/lib\/python3.12\/dist-packages (from openjij) (2.0.2)\r\nCollecting dimod&lt;0.13.0,&gt;=0.9.11 (from openjij)\r\n  Downloading dimod-0.12.21-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (4.0 kB)\r\nCollecting jij-cimod&lt;1.8.0,&gt;=1.7.0 (from openjij)\r\n  Downloading jij_cimod-1.7.3-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (10.0 kB)\r\nCollecting scipy&lt;1.16,&gt;=1.5.4 (from jij-cimod&lt;1.8.0,&gt;=1.7.0-&gt;openjij)\r\n  Downloading scipy-1.15.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)\r\n     <span class=\"ansi-black-intense-fg\">\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501<\/span> <span class=\"ansi-green-fg\">62.0\/62.0 kB<\/span> <span class=\"ansi-red-fg\">2.1 MB\/s<\/span> eta <span class=\"ansi-cyan-fg\">0:00:00<\/span>\r\nDownloading openjij-0.11.6-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (11.9 MB)\r\n   <span class=\"ansi-black-intense-fg\">\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501<\/span> <span class=\"ansi-green-fg\">11.9\/11.9 MB<\/span> <span class=\"ansi-red-fg\">11.4 MB\/s<\/span> eta <span class=\"ansi-cyan-fg\">0:00:00<\/span>\r\nDownloading dimod-0.12.21-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (8.9 MB)\r\n   <span class=\"ansi-black-intense-fg\">\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501<\/span> <span class=\"ansi-green-fg\">8.9\/8.9 MB<\/span> <span class=\"ansi-red-fg\">62.0 MB\/s<\/span> eta <span class=\"ansi-cyan-fg\">0:00:00<\/span>\r\nDownloading jij_cimod-1.7.3-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (11.6 MB)\r\n   <span class=\"ansi-black-intense-fg\">\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501<\/span> <span class=\"ansi-green-fg\">11.6\/11.6 MB<\/span> <span class=\"ansi-red-fg\">12.3 MB\/s<\/span> eta <span class=\"ansi-cyan-fg\">0:00:00<\/span>\r\nDownloading scipy-1.15.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (37.3 MB)\r\n   <span class=\"ansi-black-intense-fg\">\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501<\/span> <span class=\"ansi-green-fg\">37.3\/37.3 MB<\/span> <span class=\"ansi-red-fg\">13.7 MB\/s<\/span> eta <span class=\"ansi-cyan-fg\">0:00:00<\/span>\r\nInstalling collected packages: scipy, dimod, jij-cimod, openjij\r\n  Attempting uninstall: scipy\r\n    Found existing installation: scipy 1.16.3\r\n    Uninstalling scipy-1.16.3:\r\n      Successfully uninstalled scipy-1.16.3\r\nSuccessfully installed dimod-0.12.21 jij-cimod-1.7.3 openjij-0.11.6 scipy-1.15.3\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"kn\">import<\/span><span class=\"w\"> <\/span><span class=\"nn\">numpy<\/span><span class=\"w\"> <\/span><span class=\"k\">as<\/span><span class=\"w\"> <\/span><span class=\"nn\">np<\/span>\r\n<span class=\"kn\">import<\/span><span class=\"w\"> <\/span><span class=\"nn\">matplotlib.pyplot<\/span><span class=\"w\"> <\/span><span class=\"k\">as<\/span><span class=\"w\"> <\/span><span class=\"nn\">plt<\/span>\r\n<span class=\"kn\">import<\/span><span class=\"w\"> <\/span><span class=\"nn\">openjij<\/span><span class=\"w\"> <\/span><span class=\"k\">as<\/span><span class=\"w\"> <\/span><span class=\"nn\">oj<\/span>\r\n<span class=\"kn\">import<\/span><span class=\"w\"> <\/span><span class=\"nn\">itertools<\/span>\r\n<span class=\"kn\">from<\/span><span class=\"w\"> <\/span><span class=\"nn\">scipy.special<\/span><span class=\"w\"> <\/span><span class=\"kn\">import<\/span> <span class=\"n\">logsumexp<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"BAS%E3%83%87%E3%83%BC%E3%82%BF%E3%82%BB%E3%83%83%E3%83%88%E3%81%AE%E6%BA%96%E5%82%99\"><\/span>BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u6e96\u5099<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"BAS%E3%83%87%E3%83%BC%E3%82%BF%E3%81%AE%E4%BD%9C%E6%88%90\"><\/span>BAS\u30c7\u30fc\u30bf\u306e\u4f5c\u6210<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u6a2a\u7e1e\u306e\u30c7\u30fc\u30bf(Bars)\u3068\u7e26\u7e1e\u306e\u30c7\u30fc\u30bf(Stripes)\u304b\u3089\u6210\u308bBAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u4f5c\u6210\u3057\u307e\u3059\u3002\u753b\u50cf\u306e\u30b5\u30a4\u30ba\u306f64\u30d3\u30c3\u30c8\u306b\u3057\u3001\u6700\u5f8c\u306e2\u30d3\u30c3\u30c8\u3092\u753b\u50cf\u5206\u985e\u306e\u5224\u5b9a\u306b\u4f7f\u3046\u305f\u3081\u3001\u6a2a\u7e1e\u306e\u6642\u306f01\u3001\u7e26\u7e1e\u306e\u6642\u306f10\u306e\u30e9\u30d9\u30eb\u3092\u4ed8\u3051\u307e\u3059\u3002256\u679a\u306eBars\u3068256\u679a\u306eStripes\u306e\u8a08512\u679a\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304c\u4f5c\u6210\u3055\u308c\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">generate_bas_dataset<\/span><span class=\"p\">():<\/span>\r\n    <span class=\"c1\">#\u753b\u50cf\u306e\u30b5\u30a4\u30ba<\/span>\r\n    <span class=\"n\">size<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">8<\/span>\r\n\r\n    <span class=\"c1\"># \u5168\u3066\u306e 8\u30d3\u30c3\u30c8\u306e\u30d1\u30bf\u30fc\u30f3\u3092\u751f\u6210(256\u901a\u308a)<\/span>\r\n    <span class=\"n\">all_patterns<\/span> <span class=\"o\">=<\/span> <span class=\"nb\">list<\/span><span class=\"p\">(<\/span><span class=\"n\">itertools<\/span><span class=\"o\">.<\/span><span class=\"n\">product<\/span><span class=\"p\">([<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">],<\/span> <span class=\"n\">repeat<\/span><span class=\"o\">=<\/span><span class=\"n\">size<\/span><span class=\"p\">))<\/span>\r\n    <span class=\"n\">all_patterns<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">(<\/span><span class=\"n\">all_patterns<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"n\">dataset<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n\r\n    <span class=\"c1\"># Bars (\u6a2a\u7e1e) \u306e\u751f\u6210(\u5404\u884c\u304c\u540c\u3058\u5024\u3092\u6301\u3064\u30d1\u30bf\u30fc\u30f3)<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">pat<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">all_patterns<\/span><span class=\"p\">:<\/span>\r\n\r\n        <span class=\"c1\"># \u884c\u3054\u3068\u306bON\/OFF\u304c\u6c7a\u307e\u308b<\/span>\r\n        <span class=\"c1\">#pat\u306f\u4e00\u6b21\u5143\u914d\u5217\u3001pat.reshape(-1, 1)\u3067\u7e26\u30d9\u30af\u30c8\u30eb\u306e2\u6b21\u5143\u914d\u5217(8, 1)\u3092\u4f5c\u6210<\/span>\r\n        <span class=\"c1\">#np.tile\u3067\u540c\u3058\u30bf\u30a4\u30eb\u3092\u6577\u304d\u8a70\u3081\u308b\u3002(1, size=8)\u3088\u308a\u7e26\u65b9\u5411\u306b8\u56de\u540c\u3058\u3082\u306e\u3092\u30b3\u30d4\u30fc\u3057\u3066\u4e26\u3079\u308b\u3002<\/span>\r\n        <span class=\"n\">img<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">tile<\/span><span class=\"p\">(<\/span><span class=\"n\">pat<\/span><span class=\"o\">.<\/span><span class=\"n\">reshape<\/span><span class=\"p\">(<\/span><span class=\"o\">-<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">),<\/span> <span class=\"p\">(<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">size<\/span><span class=\"p\">))<\/span>\r\n\r\n        <span class=\"c1\"># \u30d5\u30e9\u30c3\u30c8\u5316\u3057\u30661\u6b21\u5143\u914d\u5217 (64\u30d3\u30c3\u30c8) \u306b\u3059\u308b<\/span>\r\n        <span class=\"n\">flat_img<\/span> <span class=\"o\">=<\/span> <span class=\"n\">img<\/span><span class=\"o\">.<\/span><span class=\"n\">flatten<\/span><span class=\"p\">()<\/span>\r\n\r\n        <span class=\"c1\"># 64\u30d3\u30c3\u30c8\u753b\u50cf\u304b\u3089\u5148\u982d62\u30d3\u30c3\u30c8\u3092\u53d6\u5f97\uff08\u5b9f\u8cea\u7684\u306b\u6700\u5f8c\u306e2\u30d4\u30af\u30bb\u30eb\u3092\u524a\u9664\uff09<\/span>\r\n        <span class=\"n\">input_bits<\/span> <span class=\"o\">=<\/span> <span class=\"n\">flat_img<\/span><span class=\"p\">[:<\/span><span class=\"mi\">62<\/span><span class=\"p\">]<\/span>\r\n\r\n        <span class=\"c1\"># \u30e9\u30d9\u30ebBars = 01<\/span>\r\n        <span class=\"n\">label<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">([<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">])<\/span>\r\n\r\n        <span class=\"c1\"># 62\u30d3\u30c3\u30c8\u306e\u30c7\u30fc\u30bf + 2\u30d3\u30c3\u30c8\u306e\u30e9\u30d9\u30eb<\/span>\r\n        <span class=\"n\">record<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">concatenate<\/span><span class=\"p\">([<\/span><span class=\"n\">input_bits<\/span><span class=\"p\">,<\/span> <span class=\"n\">label<\/span><span class=\"p\">])<\/span>\r\n        <span class=\"n\">dataset<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">record<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># Stripes (\u7e26\u7e1e) \u306e\u751f\u6210(\u5404\u5217\u304c\u540c\u3058\u5024\u3092\u6301\u3064\u30d1\u30bf\u30fc\u30f3)<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">pat<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">all_patterns<\/span><span class=\"p\">:<\/span>\r\n\r\n        <span class=\"n\">img<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">tile<\/span><span class=\"p\">(<\/span><span class=\"n\">pat<\/span><span class=\"o\">.<\/span><span class=\"n\">reshape<\/span><span class=\"p\">(<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mi\">1<\/span><span class=\"p\">),<\/span> <span class=\"p\">(<\/span><span class=\"n\">size<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">))<\/span>\r\n\r\n        <span class=\"n\">flat_img<\/span> <span class=\"o\">=<\/span> <span class=\"n\">img<\/span><span class=\"o\">.<\/span><span class=\"n\">flatten<\/span><span class=\"p\">()<\/span>\r\n\r\n        <span class=\"n\">input_bits<\/span> <span class=\"o\">=<\/span> <span class=\"n\">flat_img<\/span><span class=\"p\">[:<\/span><span class=\"mi\">62<\/span><span class=\"p\">]<\/span>\r\n\r\n        <span class=\"c1\"># \u30e9\u30d9\u30ebStripes = 10<\/span>\r\n        <span class=\"n\">label<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">([<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span><span class=\"p\">])<\/span>\r\n\r\n        <span class=\"n\">record<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">concatenate<\/span><span class=\"p\">([<\/span><span class=\"n\">input_bits<\/span><span class=\"p\">,<\/span> <span class=\"n\">label<\/span><span class=\"p\">])<\/span>\r\n        <span class=\"n\">dataset<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">record<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"k\">return<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">(<\/span><span class=\"n\">dataset<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"BAS%E3%83%87%E3%83%BC%E3%82%BF%E3%81%AE%E7%A2%BA%E8%AA%8D\"><\/span>BAS\u30c7\u30fc\u30bf\u306e\u78ba\u8a8d<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u6b63\u3057\u304fBAS\u30c7\u30fc\u30bf\u304c\u4f5c\u6210\u3055\u308c\u3066\u3044\u308b\u304b\u78ba\u8a8d\u3059\u308b\u305f\u3081\u306b\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304b\u3089\u30e9\u30f3\u30c0\u30e0\u306b5\u679a\u3001\u753b\u50cf\u3068\u3057\u3066\u53ef\u8996\u5316\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">visualize_samples<\/span><span class=\"p\">(<\/span><span class=\"n\">dataset<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_samples<\/span><span class=\"o\">=<\/span><span class=\"mi\">5<\/span><span class=\"p\">):<\/span>\r\n\r\n    <span class=\"c1\"># \u30e9\u30f3\u30c0\u30e0\u306b\u30b5\u30f3\u30d7\u30eb\u62bd\u51fa<\/span>\r\n    <span class=\"n\">indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">choice<\/span><span class=\"p\">(<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">dataset<\/span><span class=\"p\">),<\/span> <span class=\"n\">num_samples<\/span><span class=\"p\">,<\/span> <span class=\"n\">replace<\/span><span class=\"o\">=<\/span><span class=\"kc\">False<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"n\">fig<\/span><span class=\"p\">,<\/span> <span class=\"n\">axes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">subplots<\/span><span class=\"p\">(<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_samples<\/span><span class=\"p\">,<\/span> <span class=\"n\">figsize<\/span><span class=\"o\">=<\/span><span class=\"p\">(<\/span><span class=\"mi\">15<\/span><span class=\"p\">,<\/span> <span class=\"mi\">3<\/span><span class=\"p\">))<\/span>\r\n\r\n    <span class=\"k\">for<\/span> <span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"n\">idx<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">enumerate<\/span><span class=\"p\">(<\/span><span class=\"n\">indices<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">record<\/span> <span class=\"o\">=<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">[<\/span><span class=\"n\">idx<\/span><span class=\"p\">]<\/span>\r\n\r\n        <span class=\"c1\"># \u6700\u5f8c\u306e2\u30d3\u30c3\u30c8\u306f\u30e9\u30d9\u30eb<\/span>\r\n        <span class=\"n\">label_bits<\/span> <span class=\"o\">=<\/span> <span class=\"n\">record<\/span><span class=\"p\">[<\/span><span class=\"o\">-<\/span><span class=\"mi\">2<\/span><span class=\"p\">:]<\/span>\r\n        <span class=\"k\">if<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array_equal<\/span><span class=\"p\">(<\/span><span class=\"n\">label_bits<\/span><span class=\"p\">,<\/span> <span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">]):<\/span>\r\n            <span class=\"n\">label_name<\/span> <span class=\"o\">=<\/span> <span class=\"s2\">\"Bar (01)\"<\/span>\r\n        <span class=\"k\">elif<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array_equal<\/span><span class=\"p\">(<\/span><span class=\"n\">label_bits<\/span><span class=\"p\">,<\/span> <span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span><span class=\"p\">]):<\/span>\r\n            <span class=\"n\">label_name<\/span> <span class=\"o\">=<\/span> <span class=\"s2\">\"Stripe (10)\"<\/span>\r\n        <span class=\"k\">else<\/span><span class=\"p\">:<\/span>\r\n            <span class=\"n\">label_name<\/span> <span class=\"o\">=<\/span> <span class=\"s2\">\"Unknown\"<\/span>\r\n\r\n        <span class=\"c1\"># \u30e9\u30d9\u30eb\u4ed8\u304d\u306eBAS\u30c7\u30fc\u30bf\u306e\u753b\u50cf<\/span>\r\n        <span class=\"n\">img_reconstructed<\/span> <span class=\"o\">=<\/span> <span class=\"n\">record<\/span><span class=\"o\">.<\/span><span class=\"n\">reshape<\/span><span class=\"p\">(<\/span><span class=\"mi\">8<\/span><span class=\"p\">,<\/span> <span class=\"mi\">8<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">imshow<\/span><span class=\"p\">(<\/span><span class=\"n\">img_reconstructed<\/span><span class=\"p\">,<\/span> <span class=\"n\">cmap<\/span><span class=\"o\">=<\/span><span class=\"s1\">'cividis'<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u8ad6\u6587\u306e\u9ec4\u8272\u30fb\u9752\u306b\u8fd1\u3044\u8272\u5473<\/span>\r\n        <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_title<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"Idx: <\/span><span class=\"si\">{<\/span><span class=\"n\">idx<\/span><span class=\"si\">}<\/span><span class=\"se\">\\n<\/span><span class=\"si\">{<\/span><span class=\"n\">label_name<\/span><span class=\"si\">}<\/span><span class=\"s2\">\"<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">axis<\/span><span class=\"p\">(<\/span><span class=\"s1\">'off'<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">tight_layout<\/span><span class=\"p\">()<\/span>\r\n    <span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">show<\/span><span class=\"p\">()<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u753b\u50cf\u3092\u53ef\u8996\u5316\u3057\u307e\u3059\u3002\u9ec4\u8272\u304c1\u306b\u3001\u9ed2\u304c0\u306b\u5bfe\u5fdc\u3057\u307e\u3059\u3002\u753b\u50cf\u306e\u53f3\u4e0b\u304c01\u306e\u6642\u306b\u6a2a\u7e1e\u3068\u306a\u308a\u300110\u306e\u6642\u306b\u7e26\u7e1e\u3068\u306a\u308b\u69d8\u5b50\u304c\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"n\">bas_dataset<\/span> <span class=\"o\">=<\/span> <span class=\"n\">generate_bas_dataset<\/span><span class=\"p\">()<\/span>\r\n\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u5f62\u72b6: <\/span><span class=\"si\">{<\/span><span class=\"n\">bas_dataset<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"si\">}<\/span><span class=\"s2\">\"<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u671f\u5f85\u5024: (512, 64)<\/span>\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"\u5185\u8a33: Bars 256\u500b + Stripes 256\u500b\"<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u30c7\u30fc\u30bf\u306e\u53ef\u8996\u5316<\/span>\r\n<span class=\"n\">visualize_samples<\/span><span class=\"p\">(<\/span><span class=\"n\">bas_dataset<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_subarea output_stream output_stdout output_text\">\n<pre>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u5f62\u72b6: (512, 64)\r\n\u5185\u8a33: Bars 256\u500b + Stripes 256\u500b\r\n<\/pre>\n<\/div>\n<\/div>\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_png output_subarea\"><img decoding=\"async\" alt=\"No description has been provided for this image\" src=\"data:image\/png;base64,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\" \/><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"RBM%E3%81%AE%E5%AE%9F%E8%A3%85\"><\/span>RBM\u306e\u5b9f\u88c5<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"RBM%E3%81%AE%E5%9F%BA%E6%9C%AC%E3%81%AE%E5%AE%9F%E8%A3%85\"><\/span>RBM\u306e\u57fa\u672c\u306e\u5b9f\u88c5<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"fm\">__init__<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_visible<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_hidden<\/span><span class=\"p\">,<\/span> <span class=\"n\">learning_rate<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.05<\/span><span class=\"p\">):<\/span>\r\n<span class=\"w\">    <\/span><span class=\"sd\">\"\"\"<\/span>\r\n<span class=\"sd\">    n_visible: \u53ef\u8996\u5c64\u306e\u30e6\u30cb\u30c3\u30c8\u6570<\/span>\r\n<span class=\"sd\">    n_hidden: \u96a0\u308c\u5c64\u306e\u30e6\u30cb\u30c3\u30c8\u6570<\/span>\r\n<span class=\"sd\">    learning_rate: \u5b66\u7fd2\u7387<\/span>\r\n<span class=\"sd\">    W: \u91cd\u307f\u884c\u5217(0\u4ed8\u8fd1\u306e\u5024\u3067\u521d\u671f\u5316)<\/span>\r\n<span class=\"sd\">    b: \u53ef\u8996\u5c64\u306e\u30d0\u30a4\u30a2\u30b9(0\u3067\u521d\u671f\u5316)<\/span>\r\n<span class=\"sd\">    c: \u96a0\u308c\u5c64\u306e\u30d0\u30a4\u30a2\u30b9(0\u3067\u521d\u671f\u5316)<\/span>\r\n<span class=\"sd\">    \"\"\"<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span> <span class=\"o\">=<\/span> <span class=\"n\">n_visible<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_hidden<\/span> <span class=\"o\">=<\/span> <span class=\"n\">n_hidden<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">=<\/span> <span class=\"n\">learning_rate<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">normal<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.01<\/span><span class=\"p\">,<\/span> <span class=\"p\">(<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_hidden<\/span><span class=\"p\">))<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">zeros<\/span><span class=\"p\">(<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">zeros<\/span><span class=\"p\">(<\/span><span class=\"n\">n_hidden<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># \u5b9f\u9a131\u3001\u5b9f\u9a133\u3067\u30a8\u30dd\u30c3\u30af\u6bce\u306e\u6b63\u89e3\u7387\u3068\u5bfe\u6570\u5c24\u5ea6\u3092\u3082\u3068\u3081\u308b\u305f\u3081\u306b\u4fdd\u5b58\u7528\u306e\u30ea\u30b9\u30c8\u3092\u4f5c\u308b<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span> <span class=\"o\">=<\/span> <span class=\"p\">{<\/span><span class=\"s1\">'bars_acc'<\/span><span class=\"p\">:<\/span> <span class=\"p\">[],<\/span> <span class=\"s1\">'stripes_acc'<\/span><span class=\"p\">:<\/span> <span class=\"p\">[],<\/span> <span class=\"s1\">'ll'<\/span><span class=\"p\">:<\/span> <span class=\"p\">[]}<\/span>\r\n\r\n<span class=\"c1\"># \u30b7\u30b0\u30e2\u30a4\u30c9\u95a2\u6570<\/span>\r\n<span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">sigmoid<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">x<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"k\">return<\/span> <span class=\"mf\">1.0<\/span> <span class=\"o\">\/<\/span> <span class=\"p\">(<\/span><span class=\"mf\">1.0<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">exp<\/span><span class=\"p\">(<\/span><span class=\"o\">-<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">clip<\/span><span class=\"p\">(<\/span><span class=\"n\">x<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mi\">500<\/span><span class=\"p\">,<\/span> <span class=\"mi\">500<\/span><span class=\"p\">)))<\/span>\r\n\r\n<span class=\"c1\"># \u53ef\u8996\u5c64\u306e\u72b6\u614b\u304b\u3089\u96a0\u308c\u5c64\u306e\u5024\u3092\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b\u95a2\u6570<\/span>\r\n<span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">v<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"c1\"># \u96a0\u308c\u5c64\u306e\u30e6\u30cb\u30c3\u30c8\u304c1\u306b\u306a\u308b\u78ba\u7387\u3092\u53ef\u8996\u5c64\u306e\u5024\u3092\u57fa\u306b\u8a08\u7b97<\/span>\r\n    <span class=\"n\">prob_h<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sigmoid<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">v<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"p\">)<\/span> <span class=\"o\">+<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"c1\"># 0\u4ee5\u4e0a1\u4ee5\u4e0b\u306e\u4e00\u69d8\u5206\u5e03\u306b\u5f93\u3046\u4e71\u6570\u3092\u751f\u6210\u3057\u3001prob_h\u306e\u30e6\u30cb\u30c3\u30c8\u6bce\u306e\u5024\u3068\u6bd4\u8f03\u3057\u30660\u304b1\u3092\u6c7a\u3081\u308b<\/span>\r\n    <span class=\"n\">h_sample<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">rand<\/span><span class=\"p\">(<\/span><span class=\"o\">*<\/span><span class=\"n\">prob_h<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">)<\/span> <span class=\"o\">&lt;<\/span> <span class=\"n\">prob_h<\/span><span class=\"p\">)<\/span><span class=\"o\">.<\/span><span class=\"n\">astype<\/span><span class=\"p\">(<\/span><span class=\"nb\">float<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"k\">return<\/span> <span class=\"n\">prob_h<\/span><span class=\"p\">,<\/span> <span class=\"n\">h_sample<\/span>\r\n\r\n<span class=\"c1\"># \u96a0\u308c\u5c64\u306e\u72b6\u614b\u304b\u3089\u53ef\u8996\u5c64\u306e\u5024\u3092\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b\u95a2\u6570<\/span>\r\n<span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">h<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">prob_v<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sigmoid<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">h<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">)<\/span> <span class=\"o\">+<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">v_sample<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">rand<\/span><span class=\"p\">(<\/span><span class=\"o\">*<\/span><span class=\"n\">prob_v<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">)<\/span> <span class=\"o\">&lt;<\/span> <span class=\"n\">prob_v<\/span><span class=\"p\">)<\/span><span class=\"o\">.<\/span><span class=\"n\">astype<\/span><span class=\"p\">(<\/span><span class=\"nb\">float<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"k\">return<\/span> <span class=\"n\">prob_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_sample<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>RBM\u306e\u5b66\u7fd2\u3067\u306f\u91cd\u307f\u3068\u30d0\u30a4\u30a2\u30b9\u3092\u66f4\u65b0\u3059\u308b\u305f\u3081\u306b\u5f0f(1)\u3001(2)\u3001(3)\u3092\u8a08\u7b97\u3057\u307e\u3059\u3002(\u8a73\u7d30\u306f<a href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/03\/25\/d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84%e3%83%9e%e3%83%b3%e3%83%9e%e3%82%b7%e3%83%b3\/\">\u89e3\u8aac\u8a18\u4e8b<\/a>\u3068<a href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/03\/25\/%e3%83%9c%e3%83%ab%e3%83%84%e3%83%9e%e3%83%b3%e3%83%9e%e3%82%b7%e3%83%b3%e3%81%a8%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84%e3%83%9e%e3%83%b3%e3%83%9e%e3%82%b7%e3%83%b3\/\">\u7528\u8a9e\u96c6<\/a>\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002) \u671f\u5f85\u5024$\\mathbb{E}_{P_\\theta(\\vec{V},\\vec{H})}[\u22c5]$\u306e\u53b3\u5bc6\u8a08\u7b97\u306f\u56f0\u96e3\u3067\u3042\u308b\u305f\u3081\u3001\u30e2\u30c7\u30eb\u5206\u5e03\u304b\u3089\u30b5\u30f3\u30d7\u30eb\u3092\u751f\u6210\u3057\u3001\u30b5\u30f3\u30d7\u30eb\u5e73\u5747\u306b\u3088\u3063\u3066\u8fd1\u4f3c\u3057\u307e\u3059\u3002<\/p>\n<p>$$ W_{ij} \\leftarrow W_{ij} + \\eta \\left( \\mathbb{E}_{P_{\\text{data}}(\\vec{v})P_\\theta(\\vec{h}\\mid \\vec{v})}[v_i h_j] &#8211; \\mathbb{E}_{P_\\theta(\\vec{V},\\vec{H})}[v_i h_j] \\right) \\tag{1} $$<\/p>\n<p>$$ b_i \\leftarrow b_i + \\eta \\left( \\mathbb{E}_{P_{\\text{data}}(\\vec{v})P_\\theta(\\vec{h}\\mid \\vec{v})}[v_i] &#8211; \\mathbb{E}_{P_\\theta(\\vec{V},\\vec{H})}[v_i] \\right) \\tag{2}$$<\/p>\n<p>$$ c_j \\leftarrow c_j + \\eta \\left( \\mathbb{E}_{P_{\\text{data}}(\\vec{v})P_\\theta(\\vec{h}\\mid \\vec{v})}[h_j] &#8211; \\mathbb{E}_{P_\\theta(\\vec{V},\\vec{H})}[h_j] \\right) \\tag{3}$$<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u8ad6\u6587\u3067\u306f\u671f\u5f85\u5024$\\mathbb{E}_{P_\\theta(\\vec{V},\\vec{H})}[\u22c5]$\u306e\u8a08\u7b97\u306b2\u901a\u308a\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u65b9\u6cd5\u3092\u7528\u3044\u3066\u3044\u307e\u3059\u3002\u4e00\u3064\u306f\u3001\u30b3\u30f3\u30c8\u30e9\u30b9\u30c6\u30a3\u30d6\u30fb\u30c0\u30a4\u30d0\u30fc\u30b8\u30a7\u30f3\u30b9(CD)\u3068\u3044\u3046\u3088\u304f\u4f7f\u308f\u308c\u308b\u65b9\u6cd5\u3067\u3001\u3082\u3046\u4e00\u3064\u306f\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b\u65b9\u6cd5\u3067\u3059\u3002(\u8a73\u7d30\u306f<a href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/03\/25\/d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84%e3%83%9e%e3%83%b3%e3%83%9e%e3%82%b7%e3%83%b3\/\">\u89e3\u8aac\u8a18\u4e8b<\/a>\u3068<a href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/03\/25\/%e3%83%9c%e3%83%ab%e3%83%84%e3%83%9e%e3%83%b3%e3%83%9e%e3%82%b7%e3%83%b3%e3%81%a8%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84%e3%83%9e%e3%83%b3%e3%83%9e%e3%82%b7%e3%83%b3\/\">\u7528\u8a9e\u96c6<\/a>\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002)<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"CD-1%E3%81%AE%E3%82%B5%E3%83%B3%E3%83%97%E3%83%AA%E3%83%B3%E3%82%B0%E3%81%AB%E3%82%88%E3%82%8BRBM%E3%81%AE%E5%AD%A6%E7%BF%92%E9%96%A2%E6%95%B0%E3%81%AE%E5%AE%9F%E8%A3%85\"><\/span>CD-1\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308bRBM\u306e\u5b66\u7fd2\u95a2\u6570\u306e\u5b9f\u88c5<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u307e\u305a\u3001\u8a13\u7df4\u30c7\u30fc\u30bf\u306e\u4e00\u3064$\\vec{v}^{(0)}$\u3092\u53ef\u8996\u5c64\u306b\u5165\u529b\u3057\u307e\u3059\u3002\u6b21\u306b\u5f0f(4)\u3067\u8868\u3055\u308c\u308b\u78ba\u7387\u306b\u5f93\u3063\u3066\u3001\u96a0\u308c\u5c64\u306e\u5024$\\vec{h}^{(0)}$\u3092\u6c7a\u3081\u307e\u3059\u3002\u3053\u306e\u6642\u3001\u78ba\u7387\u3092\u57fa\u306b\u6c7a\u3081\u3066\u3044\u308b\u306e\u3067\u3001\u5024\u306f\u4e00\u610f\u306b\u306f\u6c7a\u307e\u308a\u307e\u305b\u3093\u3002<\/p>\n<p>$$P(H_j = 1 \\mid \\vec{v}^{(0)}) = \\sigma \\left(b_i+\\sum_i W_{ij} v_i^{(0)}\\right) \\tag{4}$$<\/p>\n<p>\u6b21\u306b\u3001\u5f97\u3089\u308c\u305f\u96a0\u308c\u30e6\u30cb\u30c3\u30c8\u304b\u3089\u5f0f(5)\u306b\u5f93\u3063\u3066\u3001\u53ef\u8996\u5c64\u306e\u5024$\\vec{v}^{(1)}$\u3092\u6c7a\u3081\u307e\u3059\u3002<\/p>\n<p>$$P(V_i = 1 \\mid \\vec{h}^{(0)}) = \\sigma \\left(c_i+\\sum_j W_{ij} h_j^{(0)}\\right) \\tag{5}$$<\/p>\n<p>\u3055\u3089\u306b\u3001\u3082\u3046\u4e00\u5ea6\u96a0\u308c\u5c64\u306e\u5024$\\vec{h}^{(1)}$\u3092\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u307e\u3059\u3002<\/p>\n<p>$$P(H_j = 1 \\mid \\vec{v}^{(1)}) = \\sigma \\left(b_i+\\sum_i W_{ij} v_i^{(1)}\\right) \\tag{6}$$<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">train_step_cd<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">batch<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">n_batch<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span>\r\n    <span class=\"c1\"># \u53ef\u8996\u5c64\u306b\u306f\u8a13\u7df4\u30c7\u30fc\u30bf\u3092\u5165\u529b<\/span>\r\n    <span class=\"n\">pos_v<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span>\r\n    <span class=\"n\">prob_h0<\/span><span class=\"p\">,<\/span> <span class=\"n\">pos_h<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u5f0f(4)<\/span>\r\n    <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">neg_v<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_h<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u5f0f(5)<\/span>\r\n    <span class=\"n\">prob_h1<\/span><span class=\"p\">,<\/span> <span class=\"n\">_<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u5f0f(6)<\/span>\r\n\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h1<\/span><span class=\"p\">))<\/span> <span class=\"o\">\/<\/span> <span class=\"n\">n_batch<\/span> <span class=\"c1\"># \u5f0f(1)<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span> <span class=\"o\">-<\/span> <span class=\"n\">neg_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u5f0f(2)<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">prob_h0<\/span> <span class=\"o\">-<\/span> <span class=\"n\">prob_h1<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u5f0f(3)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"SA%E3%81%AE%E3%82%B5%E3%83%B3%E3%83%97%E3%83%AA%E3%83%B3%E3%82%B0%E3%81%AB%E3%82%88%E3%82%8BRBM%E3%81%AE%E5%AD%A6%E7%BF%92%E9%96%A2%E6%95%B0%E3%81%AE%E5%AE%9F%E8%A3%85\"><\/span>SA\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308bRBM\u306e\u5b66\u7fd2\u95a2\u6570\u306e\u5b9f\u88c5<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>QA\u306b\u3088\u308b\u8a08\u7b97\u3092\u6a21\u3057\u305f\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3067\u5b9f\u88c5\u3057\u307e\u3059\u3002\u5177\u4f53\u7684\u306b\u306fOpenJij\u306eSAsampler\u3092\u4f7f\u3063\u3066\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u307e\u3059\u3002\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306e\u65b9\u6cd5\u306fQA\u3068\u540c\u3058\u3067\u3059\u3002<\/p>\n<ol>\n<li>QUBO\u3092\u4f5c\u308b<\/li>\n<li>\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b<\/li>\n<li>\u52fe\u914d\u3092\u8a08\u7b97\u3059\u308b<\/li>\n<li>QUBO\u3092\u66f4\u65b0\u3059\u308b<\/li>\n<li>1.\uff5e4.\u3092\u5024\u304c\u53ce\u675f\u3059\u308b\u307e\u3067\u884c\u3046<\/li>\n<\/ol>\n<p>QA\u306f\u5f0f(7)\u3092\u57fa\u306b\u4f5c\u3089\u308c\u305fQUBO\u3092\u4f7f\u3063\u3066\u3001\u30a8\u30cd\u30eb\u30ae\u30fc$E_\\theta(\\vec{v},\\vec{h})$\u3092\u6700\u5c0f\u306b\u3057\u307e\u3059\u3002<\/p>\n<p>$$ E_\\theta(\\vec{v},\\vec{h}) = -\\sum_{i=1}^{n} b_i v_i -\\sum_{j=1}^{m} c_j h_j -\\sum_{i=1}^{n}\\sum_{j=1}^{m} v_i W_{ij} h_j \\tag{7} $$<\/p>\n<p>QUBO\u306f\u4e0a\u4e09\u89d2\u884c\u5217\u3067\u3059\u3002\u5bfe\u89d2\u6210\u5206\u306f\u53ef\u8996\u30d0\u30a4\u30a2\u30b9(\u30ce\u30fc\u30c9\u6570$n$)\u3068\u96a0\u308c\u30d0\u30a4\u30a2\u30b9(\u30ce\u30fc\u30c9\u6570$m$)\u3067\u3042\u308a\u3001\u305d\u306e\u4ed6\u306f\u91cd\u307f\u3092\u8868\u3057\u307e\u3059\u3002train_step_sa\u95a2\u6570\u3092\u547c\u3073\u51fa\u3059\u6bce\u306b\u66f4\u65b0\u3055\u308c\u305f\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u4f7f\u3063\u3066QUBO\u304c\u4f5c\u6210\u3057\u76f4\u3055\u308c\u307e\u3059\u3002<\/p>\n<p>SA\u3067\u306f\u3001\u9ad8\u3044\u6e29\u5ea6(beta_min)\u304b\u3089\u4f4e\u3044\u6e29\u5ea6(beta_max)\u306b\u5909\u5316\u3055\u305b\u306a\u304c\u3089\u3001\u30a8\u30cd\u30eb\u30ae\u30fc\u304c\u6700\u5c0f\u3068\u306a\u308b$v_i$\u3068$h_j$\u306e\u5024\u3092\u63a2\u7d22\u3057\u3066\u3044\u304d\u307e\u3059\u3002\u3053\u306e\u6642\u3001num_sweeps\u306f\u3069\u306e\u304f\u3089\u3044\u306e\u7a0b\u5ea6\u3067\u6e29\u5ea6\u3092\u4e0b\u3052\u3066\u3044\u304f\u304b\u3092\u793a\u3057\u3001num_reads\u306f\u4f55\u56deSA\u3092\u884c\u3046\u304b\u3092\u793a\u3057\u307e\u3059\u3002num_sweeps\u306e\u5024\u304c\u5927\u304d\u3044\u3068\u3001\u3086\u3063\u304f\u308a\u3068\u6e29\u5ea6\u304c\u4e0b\u304c\u308b\u305f\u3081\u3001\u6700\u9069\u89e3\u304c\u898b\u3064\u304b\u308a\u3084\u3059\u304f\u3001num_reads\u306e\u5024\u304c\u5927\u304d\u3044\u3068\u3001\u30b5\u30f3\u30d7\u30eb\u304c\u5897\u3048\u308b\u306e\u3067\u3001\u5e73\u5747\u3059\u308b\u3068\u771f\u306e\u78ba\u7387\u5206\u5e03\u306b\u8fd1\u3065\u304d\u307e\u3059\u3002<br \/>\n\u4eca\u56de\u306e\u5b9f\u9a13\u3067\u306f<\/p>\n<ul>\n<li>beta_min=0.2<\/li>\n<li>beta_max=1.0<\/li>\n<li>num_reads=16<\/li>\n<li>num_sweeps=100<\/li>\n<\/ul>\n<p>\u3068\u8a2d\u5b9a\u3057\u307e\u3057\u305f\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">train_step_sa<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">batch<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_reads<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_sweeps<\/span><span class=\"o\">=<\/span><span class=\"mi\">100<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">n_batch<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span>\r\n    <span class=\"n\">pos_v<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span>\r\n    <span class=\"n\">prob_h0<\/span><span class=\"p\">,<\/span> <span class=\"n\">_<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"n\">sampler<\/span> <span class=\"o\">=<\/span> <span class=\"n\">oj<\/span><span class=\"o\">.<\/span><span class=\"n\">SASampler<\/span><span class=\"p\">()<\/span>\r\n    <span class=\"n\">qubo<\/span> <span class=\"o\">=<\/span> <span class=\"p\">{}<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">i<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">):<\/span> <span class=\"n\">qubo<\/span><span class=\"p\">[(<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"n\">i<\/span><span class=\"p\">)]<\/span> <span class=\"o\">=<\/span> <span class=\"o\">-<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># \u5bfe\u89d2\u6210\u5206\u306b\u53ef\u8996\u30d0\u30a4\u30a2\u30b9\u3092\u4ee3\u5165<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">j<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_hidden<\/span><span class=\"p\">):<\/span> <span class=\"n\">qubo<\/span><span class=\"p\">[(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"o\">+<\/span><span class=\"n\">j<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"o\">+<\/span><span class=\"n\">j<\/span><span class=\"p\">)]<\/span> <span class=\"o\">=<\/span> <span class=\"o\">-<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span><span class=\"p\">[<\/span><span class=\"n\">j<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># \u5bfe\u89d2\u6210\u5206\u306b\u96a0\u308c\u30d0\u30a4\u30a2\u30b9\u3092\u4ee3\u5165<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">i<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">j<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_hidden<\/span><span class=\"p\">):<\/span> <span class=\"n\">qubo<\/span><span class=\"p\">[(<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"o\">+<\/span><span class=\"n\">j<\/span><span class=\"p\">)]<\/span> <span class=\"o\">=<\/span> <span class=\"o\">-<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"n\">j<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># \u5bfe\u89d2\u6210\u5206\u3088\u308a\u4e0a\u5074\u306b\u91cd\u307f\u3092\u4ee3\u5165<\/span>\r\n\r\n    <span class=\"n\">response<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sampler<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_qubo<\/span><span class=\"p\">(<\/span><span class=\"n\">qubo<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_reads<\/span><span class=\"o\">=<\/span><span class=\"n\">num_reads<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_sweeps<\/span><span class=\"o\">=<\/span><span class=\"n\">num_sweeps<\/span><span class=\"p\">,<\/span> <span class=\"n\">beta_min<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.2<\/span><span class=\"p\">,<\/span> <span class=\"n\">beta_max<\/span><span class=\"o\">=<\/span><span class=\"mf\">1.0<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">neg_v<\/span> <span class=\"o\">=<\/span> <span class=\"n\">response<\/span><span class=\"o\">.<\/span><span class=\"n\">record<\/span><span class=\"o\">.<\/span><span class=\"n\">sample<\/span><span class=\"p\">[:,<\/span> <span class=\"p\">:<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">astype<\/span><span class=\"p\">(<\/span><span class=\"nb\">float<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">prob_h_model<\/span><span class=\"p\">,<\/span> <span class=\"n\">_<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># \u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u30b5\u30f3\u30d7\u30eb\u6570\u3067\u5272\u3063\u3066\u5e73\u5747\u5316\u3059\u308b<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h_model<\/span><span class=\"p\">))<\/span> <span class=\"o\">\/<\/span> <span class=\"n\">num_reads<\/span> <span class=\"c1\"># \u91cd\u307f\u3092\u5e73\u5747\u5316<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">))<\/span> <span class=\"c1\"># \u53ef\u8996\u30d0\u30a4\u30a2\u30b9\u3092\u5e73\u5747\u5316<\/span>\r\n    <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">prob_h0<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">prob_h_model<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">))<\/span> <span class=\"c1\"># \u96a0\u308c\u30d0\u30a4\u30a2\u30b9\u3092\u5e73\u5747\u5316<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"%E7%94%BB%E5%83%8F%E5%88%86%E9%A1%9E%E3%81%AE%E6%AD%A3%E8%A7%A3%E7%8E%87%E3%82%92%E3%82%82%E3%81%A8%E3%82%81%E3%82%8B%E9%96%A2%E6%95%B0\"><\/span>\u753b\u50cf\u5206\u985e\u306e\u6b63\u89e3\u7387\u3092\u3082\u3068\u3081\u308b\u95a2\u6570<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u5b9f\u9a131\u3067\u4f7f\u7528\u3059\u308b\u305f\u3081\u306b\u3001RBM\u306b\u3088\u308b\u753b\u50cf\u5206\u985e\u306e\u6b63\u89e3\u7387\u3092\u3082\u3068\u3081\u308b\u95a2\u6570\u3092\u5b9f\u88c5\u3057\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u306e\u30e9\u30d9\u30eb\u3092\u30e9\u30f3\u30c0\u30e0\u306b\u521d\u671f\u5316\u3057\u3001RBM\u3067\u30e9\u30d9\u30eb\u3092\u5224\u5b9a\u3055\u305b\u307e\u3059\u3002\u305d\u306e\u969b\u3001\u5b66\u7fd2\u3057\u305fRBM\u3067\u518d\u5ea6\u30ae\u30d6\u30b9\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u309250\u56de\u884c\u3063\u305f\u5f8c\u306b\u3001\u30e9\u30d9\u30eb\u3092\u8aad\u307f\u53d6\u308a\u307e\u3059\u3002\u305d\u306e\u5f8c\u3001\u6b63\u89e3\u30e9\u30d9\u30eb\u3068\u6bd4\u8f03\u3057\u3066\u6b63\u89e3\u7387\u3092\u8a08\u7b97\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">get_accuracy<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">test_subset<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"o\">=<\/span><span class=\"mi\">50<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"k\">if<\/span> <span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test_subset<\/span><span class=\"p\">)<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">0<\/span><span class=\"p\">:<\/span> <span class=\"k\">return<\/span> <span class=\"mf\">0.0<\/span>\r\n    <span class=\"n\">correct<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">0<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">rec<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">test_subset<\/span><span class=\"p\">:<\/span>\r\n        <span class=\"n\">true_label<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rec<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:]<\/span>\r\n        <span class=\"n\">v_curr<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">concatenate<\/span><span class=\"p\">([<\/span><span class=\"n\">rec<\/span><span class=\"p\">[:<\/span><span class=\"mi\">62<\/span><span class=\"p\">],<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">randint<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">size<\/span><span class=\"o\">=<\/span><span class=\"mi\">2<\/span><span class=\"p\">)])<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">_<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">gibbs_steps<\/span><span class=\"p\">):<\/span>\r\n            <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">h_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">v_curr<\/span><span class=\"p\">)<\/span>\r\n            <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"n\">h_s<\/span><span class=\"p\">)<\/span>\r\n            <span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">v_s<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:]<\/span> <span class=\"c1\"># Label\u90e8\u5206\u306e\u307f\u66f4\u65b0<\/span>\r\n        <span class=\"k\">if<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array_equal<\/span><span class=\"p\">(<\/span><span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:],<\/span> <span class=\"n\">true_label<\/span><span class=\"p\">):<\/span> <span class=\"n\">correct<\/span> <span class=\"o\">+=<\/span> <span class=\"mi\">1<\/span>\r\n    <span class=\"k\">return<\/span> <span class=\"n\">correct<\/span> <span class=\"o\">\/<\/span> <span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test_subset<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%99%E3%82%8B%E9%96%A2%E6%95%B0\"><\/span>\u753b\u50cf\u518d\u69cb\u6210\u3059\u308b\u95a2\u6570<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u5b9f\u9a132\u306e\u6e96\u5099\u3068\u3057\u3066\u3001\u6307\u5b9a\u3057\u305f\u7bc4\u56f2\u306e\u30d3\u30c3\u30c8\u3092\u30e9\u30f3\u30c0\u30e0\u306a0\u30681\u306e\u914d\u5217\u306b\u3057\u3066\u7834\u640d\u3055\u305b\u305f\u753b\u50cf\u3092\u518d\u69cb\u6210\u3059\u308b\u95a2\u6570\u3092\u5b9f\u88c5\u3057\u307e\u3059\u3002\u3053\u306e\u95a2\u6570\u3067\u306f\u3001\u7834\u640d\u3055\u305b\u305f\u753b\u50cf(\u305f\u3060\u3057\u3001\u30e9\u30d9\u30eb\u306e2\u30d3\u30c3\u30c8\u306f\u9664\u304f)\u3092RBM\u5b66\u7fd2\u5668\u306b\u30bb\u30c3\u30c8\u3057\u306650\u56de\u30ae\u30d6\u30b9\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3092\u884c\u3063\u305f\u5024\u3092\u8fd4\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">original_vector<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"o\">=<\/span><span class=\"mi\">50<\/span><span class=\"p\">):<\/span>\r\n<span class=\"w\">    <\/span><span class=\"sd\">\"\"\"<\/span>\r\n<span class=\"sd\">    \u6307\u5b9a\u3057\u305f\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u3092\u7834\u640d\u3055\u305b\u3001RBM\u5b66\u7fd2\u5668\u3067\u5fa9\u5143\u3059\u308b<\/span>\r\n<span class=\"sd\">    original_vector: \u5143\u306e\u753b\u50cf\u306e\u30d3\u30c3\u30c8\u914d\u5217<\/span>\r\n<span class=\"sd\">    mask_indices: \u7834\u640d\u3055\u305b\u308b\u30d3\u30c3\u30c8\u3092\u793a\u3059\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u306e\u914d\u5217<\/span>\r\n<span class=\"sd\">    gibbs_steps: \u30ae\u30d6\u30b9\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306e\u30b9\u30c6\u30c3\u30d7\u6570<\/span>\r\n<span class=\"sd\">    \"\"\"<\/span>\r\n    <span class=\"n\">corrupted_vector<\/span> <span class=\"o\">=<\/span> <span class=\"n\">original_vector<\/span><span class=\"o\">.<\/span><span class=\"n\">copy<\/span><span class=\"p\">()<\/span>\r\n    <span class=\"c1\"># \u7834\u640d\u90e8\u5206\u30920\u30681\u3067\u30e9\u30f3\u30c0\u30e0\u306b\u57cb\u3081\u308b<\/span>\r\n    <span class=\"n\">noise<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">randint<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">size<\/span><span class=\"o\">=<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">))<\/span>\r\n    <span class=\"n\">corrupted_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">noise<\/span>\r\n\r\n    <span class=\"n\">v_curr<\/span> <span class=\"o\">=<\/span> <span class=\"n\">corrupted_vector<\/span><span class=\"o\">.<\/span><span class=\"n\">copy<\/span><span class=\"p\">()<\/span>\r\n    <span class=\"n\">all_indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">arange<\/span><span class=\"p\">(<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">original_vector<\/span><span class=\"p\">))<\/span>\r\n\r\n    <span class=\"c1\"># np.setdiff1d(\u914d\u5217A, \u914d\u5217B): \u914d\u5217A\u304b\u3089\u914d\u5217B\u306b\u542b\u307e\u308c\u308b\u8981\u7d20\u3092\u9664\u3044\u305f\u3082\u306e<\/span>\r\n    <span class=\"n\">fixed_indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">setdiff1d<\/span><span class=\"p\">(<\/span><span class=\"n\">all_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"k\">for<\/span> <span class=\"n\">_<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">gibbs_steps<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">h_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">v_curr<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"n\">h_s<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"c1\"># \u56fa\u5b9a\u3059\u308b\u30d3\u30c3\u30c8<\/span>\r\n        <span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"n\">fixed_indices<\/span><span class=\"p\">]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">original_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">fixed_indices<\/span><span class=\"p\">]<\/span>\r\n        <span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">v_s<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span>\r\n\r\n    <span class=\"k\">return<\/span> <span class=\"n\">corrupted_vector<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_curr<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%AE%E3%82%A8%E3%83%A9%E3%83%BC%E6%95%B0%E3%82%92%E3%82%82%E3%81%A8%E3%82%81%E3%82%8B%E9%96%A2%E6%95%B0\"><\/span>\u753b\u50cf\u518d\u69cb\u6210\u306e\u30a8\u30e9\u30fc\u6570\u3092\u3082\u3068\u3081\u308b\u95a2\u6570<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u307e\u305f\u3001\u518d\u69cb\u6210\u3057\u305f\u753b\u50cf\u3068\u5143\u753b\u50cf\u3092\u6bd4\u8f03\u3057\u305f\u6642\u3001\u3069\u306e\u304f\u3089\u3044\u306e\u7570\u306a\u308b\u30d3\u30c3\u30c8\u304c\u3042\u308b\u304b\u8a08\u7b97\u3059\u308b\u95a2\u6570\u3092\u5b9f\u88c5\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">get_incorrect_bits<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"o\">=<\/span><span class=\"mi\">50<\/span><span class=\"p\">):<\/span>\r\n<span class=\"w\">    <\/span><span class=\"sd\">\"\"\"<\/span>\r\n<span class=\"sd\">    \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u5bfe\u3057\u3001\u7834\u640d\u3055\u308c\u305f\u9818\u57df\u306e\u518d\u69cb\u6210\u30a8\u30e9\u30fc\uff08\u8aa4\u30d3\u30c3\u30c8\u6570\uff09\u3092\u8a08\u7b97\u3059\u308b<\/span>\r\n<span class=\"sd\">    \"\"\"<\/span>\r\n    <span class=\"n\">error_list<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">original_vector<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">:<\/span>\r\n        <span class=\"c1\"># \u518d\u69cb\u6210\u3092\u5b9f\u884c<\/span>\r\n        <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">restored_vector<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">original_vector<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"c1\"># \u7834\u640d\u3055\u308c\u305f\u7bc4\u56f2\u306e\u30d3\u30c3\u30c8\u5217\u306b\u304a\u3044\u3066\u3001\u6b63\u89e3\u5024\u3068\u518d\u69cb\u6210\u5f8c\u306e\u5024\u3092\u6bd4\u8f03<\/span>\r\n        <span class=\"n\">actual<\/span> <span class=\"o\">=<\/span> <span class=\"n\">original_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># \u6b63\u89e3\u5024<\/span>\r\n        <span class=\"n\">predicted<\/span> <span class=\"o\">=<\/span> <span class=\"n\">restored_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># \u518d\u69cb\u6210\u5f8c\u306e\u5024<\/span>\r\n\r\n        <span class=\"c1\"># \u7570\u306a\u308b\u30d3\u30c3\u30c8\u306e\u6570\u3092\u30ab\u30a6\u30f3\u30c8<\/span>\r\n        <span class=\"n\">incorrect_count<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">sum<\/span><span class=\"p\">(<\/span><span class=\"n\">actual<\/span> <span class=\"o\">!=<\/span> <span class=\"n\">predicted<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">error_list<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">incorrect_count<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"k\">return<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">(<\/span><span class=\"n\">error_list<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"%E5%AF%BE%E6%95%B0%E5%B0%A4%E5%BA%A6%E3%82%92%E3%82%82%E3%81%A8%E3%82%81%E3%82%8B%E9%96%A2%E6%95%B0\"><\/span>\u5bfe\u6570\u5c24\u5ea6\u3092\u3082\u3068\u3081\u308b\u95a2\u6570<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u5b9f\u9a133\u306e\u6e96\u5099\u3068\u3057\u3066\u3001RBM\u306e\u5bfe\u6570\u5c24\u5ea6\u3092\u8a08\u7b97\u3059\u308b\u95a2\u6570\u3092\u5b9f\u88c5\u3057\u307e\u3059\u3002\u53ef\u8996\u5c64$v$\u3092\u5468\u8fba\u5316\u3057\u3066\u3001\u96a0\u308c\u5c64$h$\u306e\u3059\u3079\u3066\u306e\u548c\u3092\u3068\u308b\u3068\u3044\u3046\u624b\u6bb5\u3067\u8a08\u7b97\u3057\u307e\u3059\u3002<\/p>\n<p>\u5177\u4f53\u7684\u306a\u8a08\u7b97\u65b9\u6cd5\u3092\u8aac\u660e\u3057\u307e\u3059\u3002<\/p>\n<p>$$\\begin{align}\\log P(v) &amp;= \\log \\frac{\\sum_h e^{-E(v, h)}}{Z}\\\\ &amp;= \\log (\\sum_h e^{-E(v, h)}) &#8211; \\log Z \\tag{8} \\end{align}$$<\/p>\n<p>\u5f0f(8)\u3067\u306f\u5bfe\u6570\u5c24\u5ea6\u306f2\u3064\u306e\u9805\u306e\u5dee\u3067\u8868\u3055\u308c\u307e\u3059\u3002\u307e\u305a\u3001\u5f0f(9)\u3067\u53ef\u8996\u5c64\u3068\u96a0\u308c\u5c64\u306e\u548c\u306e\u90e8\u5206\u306b\u5206\u3051\u307e\u3059\u3002$s = b^T + h^TW$\u3068\u3057\u307e\u3057\u305f\u3002<\/p>\n<p>$$\\begin{align} Z &amp;= \\sum_{v} \\sum_{h} e^{b^Tv + c^Th + h^TWv}\\\\ &amp;= \\sum_h e^{c^Th} \\sum_v e^{(b^T + h^TW)v}\\\\ &amp;= \\sum_{h \\in \\lbrace 0, 1 \\rbrace ^m} e^{c^T h} \\sum_{v \\in \\lbrace 0, 1 \\rbrace ^n} e^{s \\cdot v} \\tag{9} \\end{align}$$<\/p>\n<p>\u6b21\u306b\u53ef\u8996\u5c64\u306b\u95a2\u3059\u308b\u548c\u306b\u3064\u3044\u3066\u3001RBM\u3067\u306f\u540c\u3058\u5c64\u5185\u3067\u7d50\u5408\u304c\u306a\u3044\u3053\u3068\u3092\u5229\u7528\u3057\u3066\u3001\u6307\u6570\u306e\u7a4d\u3067\u8868\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002(\u5f0f(10))<\/p>\n<p>$$\\begin{align} \\sum_{v \\in \\lbrace 0, 1 \\rbrace ^n} e^{s \\cdot v} &amp;= \\sum_{v_1 \\in \\lbrace 0, 1 \\rbrace} e^{s_1 v_1} \\cdots \\sum_{v_n \\in \\lbrace 0, 1 \\rbrace} e^{s_n v_n}\\\\ &amp;= \\prod_{i=1}^n \\sum_{v_i \\in \\lbrace 0, 1 \\rbrace} e^{s_i v_i}\\\\ &amp;= \\prod_{i=1}^n (1 + e^{s_i}) \\tag{10} \\end{align}$$<\/p>\n<p>\u5f0f(10)\u3092\u5f0f(9)\u306b\u4ee3\u5165\u3057\u3066\u3001\u53ef\u8996\u5c64$v$\u3092\u5468\u8fba\u5316\u3057\u307e\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u96a0\u308c\u5c64$h$\u306e\u3059\u3079\u3066\u306e\u72b6\u614b\u306e\u548c\u304c\u3082\u3068\u307e\u308c\u3070\u3001\u5f0f(11)\u3067\u8a08\u7b97\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3057\u305f\u3002<\/p>\n<p>$$\\begin{align}\\log Z &amp;= \\log (\\sum_{h \\in \\lbrace 0, 1 \\rbrace ^m} e^{c^T h} \\prod_{i=1}^n (1 + e^{s_i}))\\\\ &amp;= \\log (\\sum_{h \\in \\lbrace 0, 1 \\rbrace ^m} e^{c^T h + \\sum_{i = 1}^n \\log (1 + e^{s_i})}) \\tag{11} \\end{align}$$<\/p>\n<p>\u540c\u69d8\u306b\u3001\u524d\u534a\u306e\u9805\u306b\u3064\u3044\u3066\u3082RBM\u306e\u6027\u8cea\u3092\u5229\u7528\u3057\u3066\u5f0f(12)\u306e\u3088\u3046\u306b\u8868\u305b\u307e\u3059\u3002<\/p>\n<p>$$ \\log (\\sum_h e^{-E(v,h)})<br \/>\n= b^T v + \\sum_{j=1}^{m} \\log \\left(1 + e^{c_j + \\sum_{i=1}^{n} W_{ij}v_i} \\right) \\tag{12} $$<\/p>\n<p>\u3053\u306e\u3088\u3046\u306b\u3001\u5bfe\u6570\u5c24\u5ea6\u306f\u5f0f(11)\u3068\u5f0f(12)\u304b\u3089\u8a08\u7b97\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">get_log_likelihood<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"n\">all_hidden_states<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"c1\"># \u5206\u914d\u95a2\u6570 Z \u306e\u8a08\u7b97<\/span>\r\n    <span class=\"n\">term_h<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">all_hidden_states<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">vis_act<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">all_hidden_states<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"c1\"># logaddexp(x, y) = log(e^x + e^y)<\/span>\r\n    <span class=\"n\">log_Z<\/span> <span class=\"o\">=<\/span> <span class=\"n\">logsumexp<\/span><span class=\"p\">(<\/span><span class=\"n\">term_h<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">sum<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">logaddexp<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">vis_act<\/span><span class=\"p\">),<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">))<\/span>\r\n\r\n    <span class=\"c1\"># \u975e\u6b63\u898f\u5316\u5c24\u5ea6\u306e\u8a08\u7b97<\/span>\r\n    <span class=\"n\">data_term<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">hid_act<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">log_unnorm<\/span> <span class=\"o\">=<\/span> <span class=\"n\">data_term<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">sum<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">logaddexp<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">hid_act<\/span><span class=\"p\">),<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"k\">return<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">log_unnorm<\/span> <span class=\"o\">-<\/span> <span class=\"n\">log_Z<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"%E3%82%AF%E3%83%A9%E3%82%B9%E3%81%AB%E3%82%88%E3%82%8B%E7%B5%B1%E5%90%88\"><\/span>\u30af\u30e9\u30b9\u306b\u3088\u308b\u7d71\u5408<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u3053\u308c\u307e\u3067\u306e\u95a2\u6570\u3092\u4e00\u3064\u306e\u30af\u30e9\u30b9\u306b\u307e\u3068\u3081\u3066\u3001\u6271\u3044\u3084\u3059\u304f\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"k\">class<\/span><span class=\"w\"> <\/span><span class=\"nc\">IntegratedRBM<\/span><span class=\"p\">:<\/span>\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"fm\">__init__<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_visible<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_hidden<\/span><span class=\"p\">,<\/span> <span class=\"n\">learning_rate<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.05<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span> <span class=\"o\">=<\/span> <span class=\"n\">n_visible<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_hidden<\/span> <span class=\"o\">=<\/span> <span class=\"n\">n_hidden<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">=<\/span> <span class=\"n\">learning_rate<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">normal<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.01<\/span><span class=\"p\">,<\/span> <span class=\"p\">(<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_hidden<\/span><span class=\"p\">))<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">zeros<\/span><span class=\"p\">(<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">zeros<\/span><span class=\"p\">(<\/span><span class=\"n\">n_hidden<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"c1\"># \u5c65\u6b74\u4fdd\u5b58\u7528\uff1abars\u6b63\u89e3\u7387\u3001stripes\u6b63\u89e3\u7387\u3001\u5bfe\u6570\u5c24\u5ea6<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span> <span class=\"o\">=<\/span> <span class=\"p\">{<\/span><span class=\"s1\">'bars_acc'<\/span><span class=\"p\">:<\/span> <span class=\"p\">[],<\/span> <span class=\"s1\">'stripes_acc'<\/span><span class=\"p\">:<\/span> <span class=\"p\">[],<\/span> <span class=\"s1\">'ll'<\/span><span class=\"p\">:<\/span> <span class=\"p\">[]}<\/span>\r\n\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">sigmoid<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">x<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"k\">return<\/span> <span class=\"mf\">1.0<\/span> <span class=\"o\">\/<\/span> <span class=\"p\">(<\/span><span class=\"mf\">1.0<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">exp<\/span><span class=\"p\">(<\/span><span class=\"o\">-<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">clip<\/span><span class=\"p\">(<\/span><span class=\"n\">x<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mi\">500<\/span><span class=\"p\">,<\/span> <span class=\"mi\">500<\/span><span class=\"p\">)))<\/span>\r\n\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">v<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">prob_h<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sigmoid<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">v<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"p\">)<\/span> <span class=\"o\">+<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">h_sample<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">rand<\/span><span class=\"p\">(<\/span><span class=\"o\">*<\/span><span class=\"n\">prob_h<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">)<\/span> <span class=\"o\">&lt;<\/span> <span class=\"n\">prob_h<\/span><span class=\"p\">)<\/span><span class=\"o\">.<\/span><span class=\"n\">astype<\/span><span class=\"p\">(<\/span><span class=\"nb\">float<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"k\">return<\/span> <span class=\"n\">prob_h<\/span><span class=\"p\">,<\/span> <span class=\"n\">h_sample<\/span>\r\n\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">h<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">prob_v<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sigmoid<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">h<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">)<\/span> <span class=\"o\">+<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">v_sample<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">rand<\/span><span class=\"p\">(<\/span><span class=\"o\">*<\/span><span class=\"n\">prob_v<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">)<\/span> <span class=\"o\">&lt;<\/span> <span class=\"n\">prob_v<\/span><span class=\"p\">)<\/span><span class=\"o\">.<\/span><span class=\"n\">astype<\/span><span class=\"p\">(<\/span><span class=\"nb\">float<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"k\">return<\/span> <span class=\"n\">prob_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_sample<\/span>\r\n\r\n    <span class=\"c1\"># CD-1\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308b\u5b66\u7fd2<\/span>\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">train_step_cd<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">batch<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">n_batch<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span>\r\n        <span class=\"n\">pos_v<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span>\r\n        <span class=\"n\">prob_h0<\/span><span class=\"p\">,<\/span> <span class=\"n\">pos_h<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">neg_v<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_h<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">prob_h1<\/span><span class=\"p\">,<\/span> <span class=\"n\">_<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h1<\/span><span class=\"p\">))<\/span> <span class=\"o\">\/<\/span> <span class=\"n\">n_batch<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span> <span class=\"o\">-<\/span> <span class=\"n\">neg_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">prob_h0<\/span> <span class=\"o\">-<\/span> <span class=\"n\">prob_h1<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># SA\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308b\u5b66\u7fd2<\/span>\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">train_step_sa<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">batch<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_reads<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_sweeps<\/span><span class=\"o\">=<\/span><span class=\"mi\">100<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">n_batch<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span><span class=\"o\">.<\/span><span class=\"n\">shape<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span>\r\n        <span class=\"n\">pos_v<\/span> <span class=\"o\">=<\/span> <span class=\"n\">batch<\/span>\r\n        <span class=\"n\">prob_h0<\/span><span class=\"p\">,<\/span> <span class=\"n\">_<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"n\">sampler<\/span> <span class=\"o\">=<\/span> <span class=\"n\">oj<\/span><span class=\"o\">.<\/span><span class=\"n\">SASampler<\/span><span class=\"p\">()<\/span>\r\n        <span class=\"n\">qubo<\/span> <span class=\"o\">=<\/span> <span class=\"p\">{}<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">i<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">):<\/span> <span class=\"n\">qubo<\/span><span class=\"p\">[(<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"n\">i<\/span><span class=\"p\">)]<\/span> <span class=\"o\">=<\/span> <span class=\"o\">-<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">]<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">j<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_hidden<\/span><span class=\"p\">):<\/span> <span class=\"n\">qubo<\/span><span class=\"p\">[(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"o\">+<\/span><span class=\"n\">j<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"o\">+<\/span><span class=\"n\">j<\/span><span class=\"p\">)]<\/span> <span class=\"o\">=<\/span> <span class=\"o\">-<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span><span class=\"p\">[<\/span><span class=\"n\">j<\/span><span class=\"p\">]<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">i<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">):<\/span>\r\n            <span class=\"k\">for<\/span> <span class=\"n\">j<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_hidden<\/span><span class=\"p\">):<\/span> <span class=\"n\">qubo<\/span><span class=\"p\">[(<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"o\">+<\/span><span class=\"n\">j<\/span><span class=\"p\">)]<\/span> <span class=\"o\">=<\/span> <span class=\"o\">-<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"n\">j<\/span><span class=\"p\">]<\/span>\r\n\r\n        <span class=\"n\">response<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sampler<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_qubo<\/span><span class=\"p\">(<\/span><span class=\"n\">qubo<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_reads<\/span><span class=\"o\">=<\/span><span class=\"n\">num_reads<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_sweeps<\/span><span class=\"o\">=<\/span><span class=\"n\">num_sweeps<\/span><span class=\"p\">,<\/span> <span class=\"n\">beta_min<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.2<\/span><span class=\"p\">,<\/span> <span class=\"n\">beta_max<\/span><span class=\"o\">=<\/span><span class=\"mf\">1.0<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">neg_v<\/span> <span class=\"o\">=<\/span> <span class=\"n\">response<\/span><span class=\"o\">.<\/span><span class=\"n\">record<\/span><span class=\"o\">.<\/span><span class=\"n\">sample<\/span><span class=\"p\">[:,<\/span> <span class=\"p\">:<\/span><span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">astype<\/span><span class=\"p\">(<\/span><span class=\"nb\">float<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">prob_h_model<\/span><span class=\"p\">,<\/span> <span class=\"n\">_<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">,<\/span> <span class=\"n\">prob_h_model<\/span><span class=\"p\">))<\/span> <span class=\"o\">\/<\/span> <span class=\"n\">num_reads<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">pos_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">neg_v<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">))<\/span>\r\n        <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">+=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">lr<\/span> <span class=\"o\">*<\/span> <span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">prob_h0<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">prob_h_model<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">))<\/span>\r\n\r\n    <span class=\"c1\"># \u753b\u50cf\u5206\u985e\u306e\u6b63\u89e3\u7387<\/span>\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">get_accuracy<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">test_subset<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"o\">=<\/span><span class=\"mi\">50<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"k\">if<\/span> <span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test_subset<\/span><span class=\"p\">)<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">0<\/span><span class=\"p\">:<\/span> <span class=\"k\">return<\/span> <span class=\"mf\">0.0<\/span>\r\n        <span class=\"n\">correct<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">0<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">rec<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">test_subset<\/span><span class=\"p\">:<\/span>\r\n            <span class=\"n\">true_label<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rec<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:]<\/span>\r\n            <span class=\"n\">v_curr<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">concatenate<\/span><span class=\"p\">([<\/span><span class=\"n\">rec<\/span><span class=\"p\">[:<\/span><span class=\"mi\">62<\/span><span class=\"p\">],<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">randint<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">size<\/span><span class=\"o\">=<\/span><span class=\"mi\">2<\/span><span class=\"p\">)])<\/span>\r\n            <span class=\"k\">for<\/span> <span class=\"n\">_<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">gibbs_steps<\/span><span class=\"p\">):<\/span>\r\n                <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">h_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">v_curr<\/span><span class=\"p\">)<\/span>\r\n                <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"n\">h_s<\/span><span class=\"p\">)<\/span>\r\n                <span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">v_s<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:]<\/span>\r\n            <span class=\"k\">if<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array_equal<\/span><span class=\"p\">(<\/span><span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">:],<\/span> <span class=\"n\">true_label<\/span><span class=\"p\">):<\/span> <span class=\"n\">correct<\/span> <span class=\"o\">+=<\/span> <span class=\"mi\">1<\/span>\r\n        <span class=\"k\">return<\/span> <span class=\"n\">correct<\/span> <span class=\"o\">\/<\/span> <span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test_subset<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># \u753b\u50cf\u518d\u69cb\u6210<\/span>\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">original_vector<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"o\">=<\/span><span class=\"mi\">50<\/span><span class=\"p\">):<\/span>\r\n\r\n        <span class=\"n\">corrupted_vector<\/span> <span class=\"o\">=<\/span> <span class=\"n\">original_vector<\/span><span class=\"o\">.<\/span><span class=\"n\">copy<\/span><span class=\"p\">()<\/span>\r\n\r\n        <span class=\"n\">noise<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">randint<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">size<\/span><span class=\"o\">=<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">))<\/span>\r\n        <span class=\"n\">corrupted_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">noise<\/span>\r\n\r\n        <span class=\"n\">v_curr<\/span> <span class=\"o\">=<\/span> <span class=\"n\">corrupted_vector<\/span><span class=\"o\">.<\/span><span class=\"n\">copy<\/span><span class=\"p\">()<\/span>\r\n        <span class=\"n\">all_indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">arange<\/span><span class=\"p\">(<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">original_vector<\/span><span class=\"p\">))<\/span>\r\n        <span class=\"n\">fixed_indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">setdiff1d<\/span><span class=\"p\">(<\/span><span class=\"n\">all_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"k\">for<\/span> <span class=\"n\">_<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">gibbs_steps<\/span><span class=\"p\">):<\/span>\r\n            <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">h_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_h_given_v<\/span><span class=\"p\">(<\/span><span class=\"n\">v_curr<\/span><span class=\"p\">)<\/span>\r\n            <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_s<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">sample_v_given_h<\/span><span class=\"p\">(<\/span><span class=\"n\">h_s<\/span><span class=\"p\">)<\/span>\r\n\r\n            <span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"n\">fixed_indices<\/span><span class=\"p\">]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">original_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">fixed_indices<\/span><span class=\"p\">]<\/span>\r\n            <span class=\"n\">v_curr<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span> <span class=\"o\">=<\/span> <span class=\"n\">v_s<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span>\r\n\r\n        <span class=\"k\">return<\/span> <span class=\"n\">corrupted_vector<\/span><span class=\"p\">,<\/span> <span class=\"n\">v_curr<\/span>\r\n\r\n    <span class=\"c1\"># \u753b\u50cf\u518d\u69cb\u6210\u306e\u30a8\u30e9\u30fc\u6570<\/span>\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">get_incorrect_bits<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"o\">=<\/span><span class=\"mi\">50<\/span><span class=\"p\">):<\/span>\r\n\r\n        <span class=\"n\">error_list<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">original_vector<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">:<\/span>\r\n            <span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">restored_vector<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">original_vector<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">,<\/span> <span class=\"n\">gibbs_steps<\/span><span class=\"p\">)<\/span>\r\n\r\n            <span class=\"n\">actual<\/span> <span class=\"o\">=<\/span> <span class=\"n\">original_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span>\r\n            <span class=\"n\">predicted<\/span> <span class=\"o\">=<\/span> <span class=\"n\">restored_vector<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">]<\/span>\r\n\r\n            <span class=\"n\">incorrect_count<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">sum<\/span><span class=\"p\">(<\/span><span class=\"n\">actual<\/span> <span class=\"o\">!=<\/span> <span class=\"n\">predicted<\/span><span class=\"p\">)<\/span>\r\n            <span class=\"n\">error_list<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">incorrect_count<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"k\">return<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">(<\/span><span class=\"n\">error_list<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># \u5bfe\u6570\u5c24\u5ea6<\/span>\r\n    <span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">get_log_likelihood<\/span><span class=\"p\">(<\/span><span class=\"bp\">self<\/span><span class=\"p\">,<\/span> <span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"n\">all_hidden_states<\/span><span class=\"p\">):<\/span>\r\n\r\n        <span class=\"n\">term_h<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">all_hidden_states<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">vis_act<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">all_hidden_states<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"o\">.<\/span><span class=\"n\">T<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">log_Z<\/span> <span class=\"o\">=<\/span> <span class=\"n\">logsumexp<\/span><span class=\"p\">(<\/span><span class=\"n\">term_h<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">sum<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">logaddexp<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">vis_act<\/span><span class=\"p\">),<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">))<\/span>\r\n\r\n        <span class=\"n\">data_term<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">b<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">hid_act<\/span> <span class=\"o\">=<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">c<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">dot<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"bp\">self<\/span><span class=\"o\">.<\/span><span class=\"n\">W<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">log_unnorm<\/span> <span class=\"o\">=<\/span> <span class=\"n\">data_term<\/span> <span class=\"o\">+<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">sum<\/span><span class=\"p\">(<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">logaddexp<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">hid_act<\/span><span class=\"p\">),<\/span> <span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"k\">return<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">mean<\/span><span class=\"p\">(<\/span><span class=\"n\">log_unnorm<\/span> <span class=\"o\">-<\/span> <span class=\"n\">log_Z<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h2><span class=\"ez-toc-section\" id=\"%E5%AE%9F%E9%A8%93\"><\/span>\u5b9f\u9a13<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"%E3%83%87%E3%83%BC%E3%82%BF%E8%A8%AD%E5%AE%9A\"><\/span>\u30c7\u30fc\u30bf\u8a2d\u5b9a<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>2\u3064\u306eRBM\u5b66\u7fd2\u5668\u3092\u8a13\u7df4\u30c7\u30fc\u30bf\u3067\u5b66\u7fd2\u3055\u305b\u3066\u3001\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3067\u8a55\u4fa1\u3057\u307e\u3059\u3002\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8512\u679a\u306e\u5185\u3001400\u679a\u3092\u8a13\u7df4\u30c7\u30fc\u30bf\u3068\u3057\u3066\u3001112\u679a\u3092\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3068\u3057\u3066\u6271\u3044\u307e\u3059\u3002\u8a13\u7df4\u30c7\u30fc\u30bf\u3068\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u306b\u542b\u307e\u308c\u308bBars\u3068Stripes\u306e\u5272\u5408\u306f\u7b49\u3057\u3044\u3088\u3046\u306b\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"c1\"># \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u751f\u6210<\/span>\r\n<span class=\"n\">dataset<\/span> <span class=\"o\">=<\/span> <span class=\"n\">generate_bas_dataset<\/span><span class=\"p\">()<\/span>\r\n\r\n<span class=\"c1\"># \u30e9\u30d9\u30eb\u3054\u3068\u306b\u30c7\u30fc\u30bf\u3092\u5206\u3051\u308b<\/span>\r\n<span class=\"c1\"># Label: Bars=[0,1], Stripes=[1,0]<\/span>\r\n<span class=\"n\">all_bars<\/span> <span class=\"o\">=<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">[(<\/span><span class=\"n\">dataset<\/span><span class=\"p\">[:,<\/span> <span class=\"mi\">62<\/span><span class=\"p\">]<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">0<\/span><span class=\"p\">)<\/span> <span class=\"o\">&amp;<\/span> <span class=\"p\">(<\/span><span class=\"n\">dataset<\/span><span class=\"p\">[:,<\/span> <span class=\"mi\">63<\/span><span class=\"p\">]<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">1<\/span><span class=\"p\">)]<\/span>\r\n<span class=\"n\">all_stripes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">[(<\/span><span class=\"n\">dataset<\/span><span class=\"p\">[:,<\/span> <span class=\"mi\">62<\/span><span class=\"p\">]<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">1<\/span><span class=\"p\">)<\/span> <span class=\"o\">&amp;<\/span> <span class=\"p\">(<\/span><span class=\"n\">dataset<\/span><span class=\"p\">[:,<\/span> <span class=\"mi\">63<\/span><span class=\"p\">]<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">0<\/span><span class=\"p\">)]<\/span>\r\n\r\n<span class=\"c1\"># \u305d\u308c\u305e\u308c\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u30b7\u30e3\u30c3\u30d5\u30eb<\/span>\r\n<span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">shuffle<\/span><span class=\"p\">(<\/span><span class=\"n\">all_bars<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">shuffle<\/span><span class=\"p\">(<\/span><span class=\"n\">all_stripes<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u8a13\u7df4\u30c7\u30fc\u30bf\u306b\u5272\u308a\u5f53\u3066\u308b\u6570\u3092\u6c7a\u3081\u308b<\/span>\r\n<span class=\"n\">n_train_per_class<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">200<\/span>\r\n\r\n<span class=\"c1\"># \u5404\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304b\u3089200\u500b\u305a\u3064\u8a13\u7df4\u30c7\u30fc\u30bf\u3078\u3001\u6b8b\u308a\u3092\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3078<\/span>\r\n<span class=\"n\">train_bars<\/span> <span class=\"o\">=<\/span> <span class=\"n\">all_bars<\/span><span class=\"p\">[:<\/span><span class=\"n\">n_train_per_class<\/span><span class=\"p\">]<\/span>\r\n<span class=\"n\">test_bars<\/span> <span class=\"o\">=<\/span> <span class=\"n\">all_bars<\/span><span class=\"p\">[<\/span><span class=\"n\">n_train_per_class<\/span><span class=\"p\">:]<\/span>\r\n\r\n<span class=\"n\">train_stripes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">all_stripes<\/span><span class=\"p\">[:<\/span><span class=\"n\">n_train_per_class<\/span><span class=\"p\">]<\/span>\r\n<span class=\"n\">test_stripes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">all_stripes<\/span><span class=\"p\">[<\/span><span class=\"n\">n_train_per_class<\/span><span class=\"p\">:]<\/span>\r\n\r\n<span class=\"c1\"># \u8a13\u7df4\u30c7\u30fc\u30bf\u3068\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u7d50\u5408\u3057\u3066\u3001\u3055\u3089\u306b\u5168\u4f53\u3092\u30b7\u30e3\u30c3\u30d5\u30eb<\/span>\r\n<span class=\"n\">train_data<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">concatenate<\/span><span class=\"p\">([<\/span><span class=\"n\">train_bars<\/span><span class=\"p\">,<\/span> <span class=\"n\">train_stripes<\/span><span class=\"p\">])<\/span>\r\n<span class=\"n\">test_data<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">concatenate<\/span><span class=\"p\">([<\/span><span class=\"n\">test_bars<\/span><span class=\"p\">,<\/span> <span class=\"n\">test_stripes<\/span><span class=\"p\">])<\/span>\r\n\r\n<span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">shuffle<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">shuffle<\/span><span class=\"p\">(<\/span><span class=\"n\">test_data<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u7d50\u679c\u306e\u78ba\u8a8d<\/span>\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"Train Set: Bars=<\/span><span class=\"si\">{<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">train_bars<\/span><span class=\"p\">)<\/span><span class=\"si\">}<\/span><span class=\"s2\">, Stripes=<\/span><span class=\"si\">{<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">train_stripes<\/span><span class=\"p\">)<\/span><span class=\"si\">}<\/span><span class=\"s2\"> (Total: <\/span><span class=\"si\">{<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">)<\/span><span class=\"si\">}<\/span><span class=\"s2\">)\"<\/span><span class=\"p\">)<\/span>\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"Test Set: Bars=<\/span><span class=\"si\">{<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test_bars<\/span><span class=\"p\">)<\/span><span class=\"si\">}<\/span><span class=\"s2\">, Stripes=<\/span><span class=\"si\">{<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test_stripes<\/span><span class=\"p\">)<\/span><span class=\"si\">}<\/span><span class=\"s2\"> (Total: <\/span><span class=\"si\">{<\/span><span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test_data<\/span><span class=\"p\">)<\/span><span class=\"si\">}<\/span><span class=\"s2\">)\"<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_subarea output_stream output_stdout output_text\">\n<pre>Train Set: Bars=200, Stripes=200 (Total: 400)\r\nTest Set: Bars=56, Stripes=56 (Total: 112)\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"%E5%AE%9F%E9%A8%931_%E7%94%BB%E5%83%8F%E5%88%86%E9%A1%9E\"><\/span>\u5b9f\u9a131 : \u753b\u50cf\u5206\u985e<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u3067\u306f\u5b9f\u969b\u306bRBM\u3092\u5b66\u7fd2\u3057\u3066\u753b\u50cf\u5206\u985e\u3092\u884c\u3044\u307e\u3059\u3002\u53ef\u8996\u5c64\u306e\u30ce\u30fc\u30c9\u309264\u3001\u96a0\u308c\u5c64\u306e\u30ce\u30fc\u30c9\u309264\u306b\u8a2d\u5b9a\u3057\u307e\u3059\u3002\u5b66\u7fd2\u7387\u306f0.10\u3067\u30d0\u30c3\u30c1\u30b5\u30a4\u30ba\u306f64\u306b\u3057\u307e\u3059\u3002\u30a8\u30dd\u30c3\u30af\u6570\u3092400\u306b\u3057\u3066\u5b66\u7fd2\u3055\u305b\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"sd\">\"\"\"<\/span>\r\n<span class=\"sd\">epochs: \u5b66\u7fd2\u56de\u6570<\/span>\r\n<span class=\"sd\">batch_size: \u30d0\u30c3\u30c1\u30b5\u30a4\u30ba<\/span>\r\n<span class=\"sd\">rbm_cd: CD-1\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308b\u5b66\u7fd2\u5668<\/span>\r\n<span class=\"sd\">rbm_sa: SA\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306b\u3088\u308b\u5b66\u7fd2\u5668<\/span>\r\n<span class=\"sd\">\"\"\"<\/span>\r\n\r\n<span class=\"c1\"># \u30e2\u30c7\u30eb\u306e\u521d\u671f\u5316<\/span>\r\n<span class=\"n\">epochs<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">400<\/span>\r\n<span class=\"n\">batch_size<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">64<\/span>\r\n<span class=\"n\">rbm_cd<\/span> <span class=\"o\">=<\/span> <span class=\"n\">IntegratedRBM<\/span><span class=\"p\">(<\/span><span class=\"mi\">64<\/span><span class=\"p\">,<\/span> <span class=\"mi\">64<\/span><span class=\"p\">,<\/span> <span class=\"n\">learning_rate<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.10<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">rbm_sa<\/span> <span class=\"o\">=<\/span> <span class=\"n\">IntegratedRBM<\/span><span class=\"p\">(<\/span><span class=\"mi\">64<\/span><span class=\"p\">,<\/span> <span class=\"mi\">64<\/span><span class=\"p\">,<\/span> <span class=\"n\">learning_rate<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.10<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"Training starting...\"<\/span><span class=\"p\">)<\/span>\r\n<span class=\"k\">for<\/span> <span class=\"n\">epoch<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">epochs<\/span> <span class=\"o\">+<\/span> <span class=\"mi\">1<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">shuffle<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">i<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">),<\/span> <span class=\"n\">batch_size<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">batch<\/span> <span class=\"o\">=<\/span> <span class=\"n\">train_data<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">:<\/span><span class=\"n\">i<\/span><span class=\"o\">+<\/span><span class=\"n\">batch_size<\/span><span class=\"p\">]<\/span>\r\n        <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">train_step_cd<\/span><span class=\"p\">(<\/span><span class=\"n\">batch<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">train_step_sa<\/span><span class=\"p\">(<\/span><span class=\"n\">batch<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_reads<\/span><span class=\"o\">=<\/span><span class=\"n\">batch_size<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># \u30a8\u30dd\u30c3\u30af\u6bce\u306b\u6b63\u89e3\u7387\u3092\u8a18\u9332<\/span>\r\n    <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'bars_acc'<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">get_accuracy<\/span><span class=\"p\">(<\/span><span class=\"n\">test_bars<\/span><span class=\"p\">))<\/span>\r\n    <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'stripes_acc'<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">get_accuracy<\/span><span class=\"p\">(<\/span><span class=\"n\">test_stripes<\/span><span class=\"p\">))<\/span>\r\n    <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'bars_acc'<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">get_accuracy<\/span><span class=\"p\">(<\/span><span class=\"n\">test_bars<\/span><span class=\"p\">))<\/span>\r\n    <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'stripes_acc'<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">get_accuracy<\/span><span class=\"p\">(<\/span><span class=\"n\">test_stripes<\/span><span class=\"p\">))<\/span>\r\n\r\n    <span class=\"k\">if<\/span> <span class=\"n\">epoch<\/span> <span class=\"o\">%<\/span> <span class=\"mi\">50<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">0<\/span><span class=\"p\">:<\/span>\r\n        <span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"Epoch <\/span><span class=\"si\">{<\/span><span class=\"n\">epoch<\/span><span class=\"si\">}<\/span><span class=\"s2\"> completed.\"<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_subarea output_stream output_stdout output_text\">\n<pre>Training starting...\r\nEpoch 50 completed.\r\nEpoch 100 completed.\r\nEpoch 150 completed.\r\nEpoch 200 completed.\r\nEpoch 250 completed.\r\nEpoch 300 completed.\r\nEpoch 350 completed.\r\nEpoch 400 completed.\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>CD-1\u5b66\u7fd2\u306eRBM\u3068SA\u5b66\u7fd2\u306eRBM\u306b\u3064\u3044\u3066\u3001Bars\u3068Stripes\u306e\u30a8\u30dd\u30c3\u30af\u6bce\u306e\u6b63\u89e3\u7387\u3092\u63cf\u5199\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"n\">fig<\/span><span class=\"p\">,<\/span> <span class=\"n\">axes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">subplots<\/span><span class=\"p\">(<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">figsize<\/span><span class=\"o\">=<\/span><span class=\"p\">(<\/span><span class=\"mi\">14<\/span><span class=\"p\">,<\/span> <span class=\"mi\">5<\/span><span class=\"p\">))<\/span>\r\n\r\n<span class=\"c1\"># Bars\u306e\u6b63\u89e3\u7387<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">plot<\/span><span class=\"p\">(<\/span><span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">epochs<\/span><span class=\"p\">),<\/span> <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'bars_acc'<\/span><span class=\"p\">],<\/span> <span class=\"n\">label<\/span><span class=\"o\">=<\/span><span class=\"s1\">'CD-1'<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"o\">=<\/span><span class=\"s1\">'black'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">plot<\/span><span class=\"p\">(<\/span><span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">epochs<\/span><span class=\"p\">),<\/span> <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'bars_acc'<\/span><span class=\"p\">],<\/span> <span class=\"n\">label<\/span><span class=\"o\">=<\/span><span class=\"s1\">'SA (OpenJij)'<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"o\">=<\/span><span class=\"s1\">'orange'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_title<\/span><span class=\"p\">(<\/span><span class=\"s1\">'Classification Accuracy (Bars)'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_xlabel<\/span><span class=\"p\">(<\/span><span class=\"s1\">'Epoch'<\/span><span class=\"p\">);<\/span> <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_ylabel<\/span><span class=\"p\">(<\/span><span class=\"s1\">'Accuracy'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_ylim<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mf\">1.05<\/span><span class=\"p\">);<\/span> <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">legend<\/span><span class=\"p\">();<\/span> <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">grid<\/span><span class=\"p\">(<\/span><span class=\"kc\">True<\/span><span class=\"p\">,<\/span> <span class=\"n\">linestyle<\/span><span class=\"o\">=<\/span><span class=\"s1\">'--'<\/span><span class=\"p\">,<\/span> <span class=\"n\">alpha<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.6<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># Stripes\u306e\u6b63\u89e3\u7387<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">plot<\/span><span class=\"p\">(<\/span><span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">epochs<\/span><span class=\"p\">),<\/span> <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'stripes_acc'<\/span><span class=\"p\">],<\/span> <span class=\"n\">label<\/span><span class=\"o\">=<\/span><span class=\"s1\">'CD-1'<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"o\">=<\/span><span class=\"s1\">'black'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">plot<\/span><span class=\"p\">(<\/span><span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"n\">epochs<\/span><span class=\"p\">),<\/span> <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">history<\/span><span class=\"p\">[<\/span><span class=\"s1\">'stripes_acc'<\/span><span class=\"p\">],<\/span> <span class=\"n\">label<\/span><span class=\"o\">=<\/span><span class=\"s1\">'SA (OpenJij)'<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"o\">=<\/span><span class=\"s1\">'orange'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_title<\/span><span class=\"p\">(<\/span><span class=\"s1\">'Classification Accuracy (Stripes)'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_xlabel<\/span><span class=\"p\">(<\/span><span class=\"s1\">'Epoch'<\/span><span class=\"p\">);<\/span> <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_ylabel<\/span><span class=\"p\">(<\/span><span class=\"s1\">'Accuracy'<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_ylim<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mf\">1.05<\/span><span class=\"p\">);<\/span> <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">legend<\/span><span class=\"p\">();<\/span> <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">grid<\/span><span class=\"p\">(<\/span><span class=\"kc\">True<\/span><span class=\"p\">,<\/span> <span class=\"n\">linestyle<\/span><span class=\"o\">=<\/span><span class=\"s1\">'--'<\/span><span class=\"p\">,<\/span> <span class=\"n\">alpha<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.6<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">tight_layout<\/span><span class=\"p\">()<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">show<\/span><span class=\"p\">()<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_png output_subarea\"><img decoding=\"async\" alt=\"No description has been provided for this image\" src=\"data:image\/png;base64,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\" \/><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"%E5%AE%9F%E9%A8%932_%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90\"><\/span>\u5b9f\u9a132 \u753b\u50cf\u518d\u69cb\u6210<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%AE%E7%B5%90%E6%9E%9C\"><\/span>\u753b\u50cf\u518d\u69cb\u6210\u306e\u7d50\u679c<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u6b21\u306e\u30b1\u30fc\u30b9A\u3001B\u3001C\u306b\u3064\u3044\u3066\u753b\u50cf\u518d\u69cb\u6210\u3092\u884c\u3063\u305f\u6642\u3001\u518d\u69cb\u6210\u3055\u308c\u305f\u753b\u50cf\u3092\u6bd4\u8f03\u3057\u307e\u3059\u3002<\/p>\n<p>\u30b1\u30fc\u30b9A: \u30e9\u30d9\u30eb(2\u30d3\u30c3\u30c8)\u3092\u7834\u640d\u3055\u305b\u305f\u5834\u5408<\/p>\n<p>\u30b1\u30fc\u30b9B: \u753b\u50cf\u306e\u53f3\u4e0b4\u00d74(16\u30d3\u30c3\u30c8)\u3092\u7834\u640d\u3055\u305b\u305f\u5834\u5408<\/p>\n<p>\u30b1\u30fc\u30b9C: \u3059\u3079\u3066\u306e\u753b\u50cf(64\u30d3\u30c3\u30c8)\u3092\u7834\u640d\u3055\u305b\u305f\u5834\u5408<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"c1\"># \u30b5\u30f3\u30d7\u30eb\u753b\u50cf\u306e\u7528\u610f<\/span>\r\n<span class=\"n\">sample_bar<\/span> <span class=\"o\">=<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">[<\/span><span class=\"mi\">10<\/span><span class=\"p\">]<\/span>      <span class=\"c1\"># Bar\u30d1\u30bf\u30fc\u30f3<\/span>\r\n<span class=\"n\">sample_stripe<\/span> <span class=\"o\">=<\/span> <span class=\"n\">dataset<\/span><span class=\"p\">[<\/span><span class=\"o\">-<\/span><span class=\"mi\">46<\/span><span class=\"p\">]<\/span>  <span class=\"c1\"># Stripe\u30d1\u30bf\u30fc\u30f3<\/span>\r\n\r\n<span class=\"c1\"># \u30b1\u30fc\u30b9A: \u30e9\u30d9\u30eb\u306e\u7834\u640d<\/span>\r\n<span class=\"n\">mask_A<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[<\/span><span class=\"mi\">62<\/span><span class=\"p\">,<\/span> <span class=\"mi\">63<\/span><span class=\"p\">]<\/span>\r\n<span class=\"n\">target_A<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sample_bar<\/span><span class=\"o\">.<\/span><span class=\"n\">copy<\/span><span class=\"p\">()<\/span>\r\n<span class=\"c1\"># target_A = sample_stripe.copy()<\/span>\r\n<span class=\"c1\"># \u30af\u30e9\u30b9\u30e1\u30bd\u30c3\u30c9\u3068\u3057\u3066\u547c\u3073\u51fa\u3057<\/span>\r\n<span class=\"n\">corp_A<\/span><span class=\"p\">,<\/span> <span class=\"n\">cd_res_A<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">target_A<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_A<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">sa_res_A<\/span>      <span class=\"o\">=<\/span> <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">target_A<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_A<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u30b1\u30fc\u30b9B: \u53f3\u4e0b4\u00d74(16\u30d3\u30c3\u30c8)\u306e\u7834\u640d<\/span>\r\n<span class=\"n\">mask_B<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n<span class=\"k\">for<\/span> <span class=\"n\">r<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"mi\">8<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">c<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"mi\">8<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">mask_B<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">r<\/span> <span class=\"o\">*<\/span> <span class=\"mi\">8<\/span> <span class=\"o\">+<\/span> <span class=\"n\">c<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">mask_B<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">(<\/span><span class=\"n\">mask_B<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"n\">target_B<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sample_bar<\/span><span class=\"o\">.<\/span><span class=\"n\">copy<\/span><span class=\"p\">()<\/span>\r\n<span class=\"c1\"># target_B = sample_stripe.copy()<\/span>\r\n<span class=\"n\">corp_B<\/span><span class=\"p\">,<\/span> <span class=\"n\">cd_res_B<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">target_B<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_B<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">sa_res_B<\/span>      <span class=\"o\">=<\/span> <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">target_B<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_B<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u30b1\u30fc\u30b9C: \u3059\u3079\u3066\u306e\u30d3\u30c3\u30c8\u306e\u7834\u640d<\/span>\r\n<span class=\"n\">mask_C<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">arange<\/span><span class=\"p\">(<\/span><span class=\"mi\">64<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">target_C<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sample_bar<\/span><span class=\"o\">.<\/span><span class=\"n\">copy<\/span><span class=\"p\">()<\/span>\r\n<span class=\"c1\"># target_C = sample_stripe.copy()<\/span>\r\n\r\n<span class=\"n\">corp_C<\/span><span class=\"p\">,<\/span> <span class=\"n\">cd_res_C<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">target_C<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_C<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">_<\/span><span class=\"p\">,<\/span> <span class=\"n\">sa_res_C<\/span>      <span class=\"o\">=<\/span> <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">reconstruct_image<\/span><span class=\"p\">(<\/span><span class=\"n\">target_C<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_C<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u63cf\u5199<\/span>\r\n<span class=\"n\">fig<\/span><span class=\"p\">,<\/span> <span class=\"n\">axes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">subplots<\/span><span class=\"p\">(<\/span><span class=\"mi\">3<\/span><span class=\"p\">,<\/span> <span class=\"mi\">3<\/span><span class=\"p\">,<\/span> <span class=\"n\">figsize<\/span><span class=\"o\">=<\/span><span class=\"p\">(<\/span><span class=\"mi\">10<\/span><span class=\"p\">,<\/span> <span class=\"mi\">10<\/span><span class=\"p\">))<\/span>\r\n<span class=\"n\">cmap<\/span> <span class=\"o\">=<\/span> <span class=\"s1\">'viridis'<\/span>\r\n<span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">to_img<\/span><span class=\"p\">(<\/span><span class=\"n\">vec<\/span><span class=\"p\">):<\/span> <span class=\"k\">return<\/span> <span class=\"n\">vec<\/span><span class=\"o\">.<\/span><span class=\"n\">reshape<\/span><span class=\"p\">(<\/span><span class=\"mi\">8<\/span><span class=\"p\">,<\/span> <span class=\"mi\">8<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"n\">titles<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[<\/span>\r\n    <span class=\"p\">(<\/span><span class=\"s2\">\"A: Label Masked(2 bits)\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">corp_A<\/span><span class=\"p\">,<\/span> <span class=\"n\">cd_res_A<\/span><span class=\"p\">,<\/span> <span class=\"n\">sa_res_A<\/span><span class=\"p\">),<\/span>\r\n    <span class=\"p\">(<\/span><span class=\"s2\">\"B: Bottom-Right Mask(16 bits)\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">corp_B<\/span><span class=\"p\">,<\/span> <span class=\"n\">cd_res_B<\/span><span class=\"p\">,<\/span> <span class=\"n\">sa_res_B<\/span><span class=\"p\">),<\/span>\r\n    <span class=\"p\">(<\/span><span class=\"s2\">\"C: Full Noise(64 bits)\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">corp_C<\/span><span class=\"p\">,<\/span> <span class=\"n\">cd_res_C<\/span><span class=\"p\">,<\/span> <span class=\"n\">sa_res_C<\/span><span class=\"p\">)<\/span>\r\n<span class=\"p\">]<\/span>\r\n\r\n<span class=\"k\">for<\/span> <span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"p\">(<\/span><span class=\"n\">title<\/span><span class=\"p\">,<\/span> <span class=\"n\">corp<\/span><span class=\"p\">,<\/span> <span class=\"n\">cd_out<\/span><span class=\"p\">,<\/span> <span class=\"n\">sa_out<\/span><span class=\"p\">)<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">enumerate<\/span><span class=\"p\">(<\/span><span class=\"n\">titles<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"c1\"># \u7834\u640d\u3057\u305f\u753b\u50cf\u306e\u8868\u793a<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">imshow<\/span><span class=\"p\">(<\/span><span class=\"n\">to_img<\/span><span class=\"p\">(<\/span><span class=\"n\">corp<\/span><span class=\"p\">),<\/span> <span class=\"n\">cmap<\/span><span class=\"o\">=<\/span><span class=\"n\">cmap<\/span><span class=\"p\">,<\/span> <span class=\"n\">vmin<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">vmax<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_title<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"<\/span><span class=\"si\">{<\/span><span class=\"n\">title<\/span><span class=\"si\">}<\/span><span class=\"se\">\\n<\/span><span class=\"s2\">Input\"<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">axis<\/span><span class=\"p\">(<\/span><span class=\"s1\">'off'<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># rbm_cd\u3067\u518d\u69cb\u6210\u3057\u305f\u753b\u50cf\u306e\u8868\u793a<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">imshow<\/span><span class=\"p\">(<\/span><span class=\"n\">to_img<\/span><span class=\"p\">(<\/span><span class=\"n\">cd_out<\/span><span class=\"p\">),<\/span> <span class=\"n\">cmap<\/span><span class=\"o\">=<\/span><span class=\"n\">cmap<\/span><span class=\"p\">,<\/span> <span class=\"n\">vmin<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">vmax<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_title<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"CD-1 Output\"<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">axis<\/span><span class=\"p\">(<\/span><span class=\"s1\">'off'<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># rbm_sa\u3067\u518d\u69cb\u6210\u3057\u305f\u753b\u50cf\u306e\u8868\u793a<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">imshow<\/span><span class=\"p\">(<\/span><span class=\"n\">to_img<\/span><span class=\"p\">(<\/span><span class=\"n\">sa_out<\/span><span class=\"p\">),<\/span> <span class=\"n\">cmap<\/span><span class=\"o\">=<\/span><span class=\"n\">cmap<\/span><span class=\"p\">,<\/span> <span class=\"n\">vmin<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">vmax<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">set_title<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"SA (OpenJij) Output\"<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">]<\/span><span class=\"o\">.<\/span><span class=\"n\">axis<\/span><span class=\"p\">(<\/span><span class=\"s1\">'off'<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">tight_layout<\/span><span class=\"p\">()<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">show<\/span><span class=\"p\">()<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_png output_subarea\"><img decoding=\"async\" alt=\"No description has been provided for this image\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAA7EAAAPeCAYAAADagZ3WAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAjX5JREFUeJzs3Xt8j+Xjx\/H3x87GGNvktI3NHEOtkoY5biJGzpXzYZZDB\/T9StlI36KQw5eiHGIoSjmLLGo6OJQS5TTpS47JIWZs1+8Pj31+Pj7bbAzdvJ6Px+fx+H7u+7qv67rv5fre7891H2zGGCMAAAAAACygwO3uAAAAAAAAuUWIBQAAAABYBiEWAAAAAGAZhFgAAAAAgGUQYgEAAAAAlkGIBQAAAABYBiEWAAAAAGAZhFgAAAAAgGUQYgEAAAAAlkGIvYVsNpv69++fb\/Xt379fNptNs2bNyrc6b5bMvr755ps3tZ369eurfv36Tsu\/++47ubu767fffsu3tnL795w1a5ZsNpv279+fL+3++9\/\/Vq1atfKlLgAAAMBq7rgQO2XKFNlstnw5yf\/iiy9ks9m0aNGifOjZ7ZO5HzabTXPnzs2yTEREhGw2m6pVq3aLe3drDBs2TJ06dVJQUJAkKSMjQ7NmzVLLli1VtmxZeXt7q1q1aho1apRSU1Nven+mTJly3T8+PPvss9q2bZuWLFmSv50CAAAALOCOC7GJiYkKDg7Wd999pz179tzu7vyjeHp6at68eU7L9+\/fr40bN8rT0\/M29Orm++GHH7R27Vr17dvXvuzcuXPq3r27jh07pr59++qtt97SQw89pPj4eD366KMyxuRb+507d9b58+ftAVq6sRB7zz33KCYm5qbPagMAAAD\/RHdUiE1JSdHGjRs1btw4+fv7KzEx8XZ36R+lWbNmWrNmjY4fP+6wfN68eSpRooQeeOCB29Szm2vmzJkKDAzUww8\/bF\/m7u6u5ORkff311xo2bJh69+6tGTNmKD4+Xl988YU+\/\/zzfGvfxcVFnp6estls+VZn+\/bt9dVXX2nfvn35VicAAABgBXdUiE1MTJSvr6+aN2+utm3bZhti9+7dq7179+Zbu2+++aYeeeQRFS9eXF5eXgoPD8\/xEuTExERVrFhRnp6eCg8P14YNG5zKHDx4UD169FCJEiXk4eGhqlWrasaMGTfUz5iYGHl4eGjhwoUOy+fNm6f27dvLxcXFaZuZM2eqYcOGCggIkIeHh6pUqaKpU6c6ldu8ebOio6Pl5+cnLy8vlStXTj169MixP8YY9enTR+7u7vr444\/ty+fOnavw8HB5eXmpWLFi6tixo37\/\/Xen7adNm6aQkBB5eXnpoYce0pdffpllO5988okaNmzoECLd3d31yCOPOJVt3bq1JGnnzp059v1K1\/p7Xn1PbHBwsH7++WetX7\/efpl35n28Fy9e1IgRI1ShQgV5enqqePHiqlOnjtasWeNQZ+PGjSVJn376aa77CQAAANwJ7rgQ+\/jjj8vd3V2dOnXS7t27tWnTJqdyjRo1UqNGjfKt3QkTJui+++7TyJEj9Z\/\/\/Eeurq5q166dli9f7lR2\/fr1evbZZ\/XUU09p5MiROnHihJo2bart27fbyxw5ckQPP\/yw1q5dq\/79+2vChAkKDQ1Vz5499dZbb113PwsWLKiYmBjNnz\/fvmzbtm36+eef9cQTT2S5zdSpUxUUFKQXX3xRY8eOVdmyZfX000\/rv\/\/9r73M0aNHFRUVpf379+vf\/\/63Jk2apCeffFLffPNNtn1JT09Xt27d9P7772vx4sV6\/PHHJUmvvvqqunTpogoVKmjcuHF69tln9fnnn6tevXr666+\/7Nu\/9957io2N1T333KMxY8YoIiJCLVu2dAq7Bw8e1IEDB3T\/\/ffn6hgdPnxYkuTn55er8rn5e17trbfeUpkyZVSpUiXNmTNHc+bM0bBhwyRJCQkJGjFihBo0aKDJkydr2LBhCgwM1NatWx3qKFKkiEJCQpScnJyrfgIAAAB3DHOH2Lx5s5Fk1qxZY4wxJiMjw5QpU8Y888wzTmWDgoJMUFDQNetMSkoykszChQtzLHfu3DmH72lpaaZatWqmYcOGDsslGUlm8+bN9mW\/\/fab8fT0NK1bt7Yv69mzpylZsqQ5fvy4w\/YdO3Y0RYoUsbeXkpJiJJmZM2fmej+WLVtmbDabOXDggDHGmCFDhpjy5csbY4yJjIw0VatWzXHfjDEmOjravo0xxixevNhIMps2bcq2D5l9feONN8zFixdNhw4djJeXl1m9erW9zP79+42Li4t59dVXHbb96aefjKurq315WlqaCQgIMDVr1jQXLlywl5s2bZqRZCIjI+3L1q5daySZpUuX5niMMjVu3Nj4+PiYkydPXrNsbv+eM2fONJJMSkqKfVnVqlUd+pmpRo0apnnz5rnqa1RUlKlcuXKuygIAAAB3ijtmJjYxMVElSpRQgwYNJF1+\/UmHDh20YMECpaenO5Tdv39\/vr3uRJK8vLzs\/\/vkyZM6deqU6tat6zR7Jkm1a9dWeHi4\/XtgYKBiYmK0evVqpaenyxijjz76SC1atJAxRsePH7d\/oqOjderUqSzrza2oqCgVK1ZMCxYskDFGCxYsUKdOnXK1b6dOndLx48cVGRmpffv26dSpU5KkokWLSpKWLVumixcv5th+Wlqa2rVrp2XLlmnFihWKioqyr\/v444+VkZGh9u3bO+z3PffcowoVKigpKUnS5UuXjx49qr59+8rd3d2+fbdu3VSkSBGH9k6cOCFJ8vX1veax+c9\/\/qO1a9fq9ddft+\/TtVzr75lXRYsW1c8\/\/6zdu3dfs6yvr6\/T\/c0AAADAnc71dncgP6Snp2vBggVq0KCBUlJS7Mtr1aqlsWPH6vPPP3cIS\/lt2bJlGjVqlH744QdduHDBvjyrB\/lUqFDBaVlYWJjOnTunY8eOqUCBAvrrr780bdo0TZs2Lcv2jh49et19dXNzU7t27TRv3jw99NBD+v3337O9lFiSkpOTFR8fr6+\/\/lrnzp1zWHfq1CkVKVJEkZGRatOmjUaMGKHx48erfv36atWqlZ544gl5eHg4bPPaa6\/p7NmzWrlypdP7XHfv3i1jTJbHKLPvkuzver26nJubm8qXL5\/ltuYaTxv+4IMP9NJLL6lnz56Ki4vLseyVrvX3vOeee3JdlySNHDlSMTExCgsLU7Vq1dS0aVN17txZ1atXdyprjMnXh0UBAAAAVnBHhNh169bpjz\/+0IIFC7RgwQKn9YmJiTctxH755Zdq2bKl6tWrpylTpqhkyZJyc3PTzJkzs3ydzbVkZGRIkp566il17do1yzJZBZq8eOKJJ\/T2228rISFBNWrUUJUqVbIst3fvXjVq1EiVKlXSuHHjVLZsWbm7u2vFihUaP368va+Z79L95ptvtHTpUq1evVo9evTQ2LFj9c0336hQoUL2OqOjo7Vq1SqNGTNG9evXd3itT0ZGhmw2m1auXJnlQ6aurCe3ihcvLunyDHl21qxZoy5duqh58+Z6++2389xGfqpXr5727t2rTz\/9VJ999pneffddjR8\/Xm+\/\/bZ69erlUPbkyZO5vncXAAAAuFPcESE2MTFRAQEBDg8byvTxxx9r8eLFevvttx0ujc0vH330kTw9PbV69WqHWceZM2dmWT6ry0R37dqlggULyt\/fX5JUuHBhpaen259Am9\/q1KmjwMBAffHFFxo9enS25ZYuXaoLFy5oyZIlCgwMtC\/PvKz3ag8\/\/LAefvhhvfrqq5o3b56efPJJLViwwCF8Pfzww+rbt68ee+wxtWvXTosXL5ar6+X\/DENCQmSMUbly5RQWFpZtvzLft7p79241bNjQvvzixYtKSUlRjRo17MsqVaokSQ4z9Ff69ttv1bp1az3wwAP68MMP7X3Jrdz8PbOS0wxqsWLF1L17d3Xv3l1nz55VvXr1lJCQ4BRir95XAAAA4G5g+Xtiz58\/r48\/\/liPPfaY2rZt6\/Tp37+\/zpw5oyVLlti3yc9X7Li4uMhmsznc\/7h\/\/3598sknWZb\/+uuvHe5p\/f333\/Xpp58qKipKLi4ucnFxUZs2bfTRRx9l+YTbY8eO3XCfbTabJk6cqPj4eHXu3DnbcpmzoVdeinvq1CmngH7y5Emny3Vr1qwpSQ6XV2dq3LixFixYoFWrVqlz5872Gd3HH39cLi4uGjFihFN9xhj7\/a0PPPCA\/P399fbbbystLc1eZtasWQ5PMJak0qVLq2zZstq8ebNTP3bu3KnmzZsrODhYy5Ytu64fOa7198yOt7e3U1+l\/7+HN1OhQoUUGhrqdBxPnTqlvXv3ZvmaIAAAAOBOZvmZ2CVLlujMmTNq2bJllusffvhh+fv7KzExUR06dJAk++t1cvtwp48++ki\/\/PKL0\/KuXbuqefPmGjdunJo2baonnnhCR48e1X\/\/+1+Fhobqxx9\/dNqmWrVqio6O1sCBA+Xh4aEpU6ZIkkaMGGEv8\/rrryspKUm1atVS7969VaVKFf3555\/aunWr1q5dqz\/\/\/DNX\/c5JTEyMYmJiciwTFRUld3d3tWjRQrGxsTp79qymT5+ugIAA\/fHHH\/Zys2fP1pQpU9S6dWuFhITozJkzmj59unx8fNSsWbMs627VqpVmzpypLl26yMfHR++8845CQkI0atQoDR06VPv371erVq1UuHBhpaSkaPHixerTp48GDx4sNzc3jRo1SrGxsWrYsKE6dOiglJQUzZw5M8t7YmNiYrR48WKHe0jPnDmj6OhonTx5UkOGDHF6HVJISIhq1659zeOYm79nVsLDwzV16lSNGjVKoaGhCggIUMOGDVWlShXVr19f4eHhKlasmDZv3qxFixapf\/\/+DtuvXbtWxphr\/g0BAACAO85teSZyPmrRooXx9PQ0f\/\/9d7ZlunXrZtzc3OyvrMnrK3ay+3z55ZfGGGPee+89U6FCBePh4WEqVapkZs6caeLj483Vh1eS6devn5k7d669\/H333WeSkpKc2j5y5Ijp16+fKVu2rHFzczP33HOPadSokZk2bZq9zPW8YicnWb1iZ8mSJaZ69erG09PTBAcHm9GjR5sZM2Y4vDJm69atplOnTiYwMNB4eHiYgIAA89hjjzm8eubKV+xcacqUKUaSGTx4sH3ZRx99ZOrUqWO8vb2Nt7e3qVSpkunXr5\/59ddfnbYtV66c8fDwMA888IDZsGGDiYyMdHp1zdatWx3+Xlf2J7tP165dczxWxuT+75nVK3YOHz5smjdvbgoXLuzwWqBRo0aZhx56yBQtWtR4eXmZSpUqmVdffdWkpaU51NmhQwdTp06da\/YRAAAAuNPYjLnGY1uBO0CjRo1UqlQpzZkz53Z35YYdPnxY5cqV04IFC5iJBQAAwF2HEIu7wrfffqu6detq9+7d9gdDWdW\/\/\/1vrVu3Tt99993t7goAAABwyxFiAQAAAACWYfmnEwMAAAAA7h6EWAAAAACAZRBiAQAAAACWQYgFAAAAAFgGIRYAAACwgN9\/\/12enp5KTk6+3V3JVwkJCbLZbA7LgoOD1a1bN\/v3VatWqVChQjp27Ngt7h3+iQixd6FZs2bJZrNp8+bNt7srOnfunBISEvTFF1\/c7q4A+IfZu3evYmNjVb58eXl6esrHx0cRERGaMGGCzp8\/by8XHBwsm80mm82mAgUKqGjRorr33nvVp08fffvtt3lqc+rUqWrXrp0CAwNls9kcTqBy68CBA+rbt6+Cg4Pl4eGhgIAAtWrV6oZPOqdMmaJZs2bdUB25tWPHDiUkJGj\/\/v23pD3Aqn766Se1bdtWQUFB8vT0VOnSpdWkSRNNmjQp223at28vm82mf\/3rX3lub+TIkapVq5YiIiKc1i1btkxNmzZV8eLF5enpqbCwMA0ePFgnTpzIczs30\/WehzZt2lShoaF67bXX8rRdcnKyWrdurRIlSsjDw0PBwcGKjY3VgQMH8lTPlW71+euKFSuUkJBwS9qyDIO7zsyZM40ks2nTptvdFXPs2DEjycTHx9\/urgD4B1m2bJnx8vIyRYsWNQMHDjTTpk0zkydPNh07djRubm6md+\/e9rJBQUGmZs2aZs6cOWbOnDlmypQpZsCAAeaee+4xksxzzz2X63aDgoJMsWLFTNOmTY2rq6vp2rVrnvr91VdfGR8fH+Pj42Oef\/558+6775pRo0aZ0NBQY7PZzMSJE\/NU35WqVq1qIiMjr3v7vFi4cKGRZJKSkm5Je4AVJScnG3d3dxMaGmpeeeUVM336dDN8+HATFRVlQkJCstzm1KlTxtPT0wQHB5uyZcuajIyMXLd39OhR4+bmZubNm+e0btCgQUaSqVGjhhk9erSZPn26iYuLMx4eHqZ06dLml19+ue79zG9ZnYdevHjRnD9\/3qFcamqqSUtLc1g2ZcoUU7BgQXP69OlctTVx4kRjs9lMSEiIeeWVV8y7775rBg0aZIoUKWKKFClikpOTr2sfbvX5a79+\/QyxzZHr7YvPAAA4S0lJUceOHRUUFKR169apZMmS9nX9+vXTnj17tHz5codtSpcuraeeesph2ejRo\/XEE09o\/PjxqlChguLi4q7Z9vr16+2zsIUKFcpTv0+ePKm2bdvKy8tLycnJCgkJsa97\/vnnFR0drWeffVbh4eF65JFH8lQ3gH+eV199VUWKFNGmTZtUtGhRh3VHjx7NcpuPPvpI6enpmjFjhho2bKgNGzYoMjIyV+3NnTtXrq6uatGihcPy+fPna+zYserQoYMSExPl4uJiX9etWzc1aNBA7dq109atW+Xq+s889Xd1dXXqm4eHh1O5Nm3aaMCAAVq4cKF69OiRY53Jycl69tlnVadOHa1atUoFCxa0r4uLi1NERITatm2rn3\/+Wb6+vvmzI7h1bneKxq139S9gXbt2Nd7e3uZ\/\/\/ufiYmJMd7e3sbPz88MGjTIXLp0yb5dSkqKkWTeeOMNM27cOBMYGGg8PT1NvXr1zE8\/\/eTQRmRkZJYzBl27djVBQUEO9V39YVYWuLv17dvXSMr1L+RBQUGmefPmWa47c+aMKVasmCldunSeZjyMMcbb2ztPM7GvvfaakWTef\/\/9LNfv27fPuLi4mOjoaPuy+Pj4LH9dzxynU1JSjDGX9\/HqsTJzjM0su379etOnTx9TrFgxU7hwYdO5c2fz559\/OtSb3RgbFBRk39fM+q7+MCsLOKpYsaKpX79+nrZp1KiRadasmTHGmMqVKztcVXIt9erVy7K9ihUrGl9fX3Pq1KkstxsxYoSRZObPn29fFhkZaapWrWo2b95sateubZ8dnjp1qtP2qampZvjw4SYkJMS4u7ubMmXKmCFDhpjU1FSHcpJMv379zOLFi03VqlWNu7u7qVKlilm5cqVDuaxmYrMaC68cl6503333mZYtW2a5r1eKjo42Li4uZt++fVmunz17tpFkXnvtNYfjcqPnr5nn1Xv37jVRUVGmYMGCpmTJkmbEiBEO\/z+UlJSU5diaWf\/MmTPt9WXV3t2Oe2IhSUpPT1d0dLSKFy+uN998U5GRkRo7dqymTZvmVPb999\/XxIkT1a9fPw0dOlTbt29Xw4YNdeTIkTy16e\/vr6lTp0qSWrdurTlz5mjOnDl6\/PHH82WfAFjT0qVLVb58+XyZrSxUqJBat26tgwcPaseOHfnQu+wtXbpUnp6eat++fZbry5Urpzp16mjdunUO9\/TmxltvvaUyZcqoUqVK9rFy2LBhDmX69++vnTt3KiEhQV26dFFiYqJatWolY0ye2qpXr54GDhwoSXrxxRft7VWuXDlP9QB3uqCgIG3ZskXbt2\/PVflDhw4pKSlJnTp1kiR16tRJixYtUlpa2jW3vXjxojZt2qT777\/fYfnu3bv166+\/KiYmRj4+Pllu26VLF0mX75m90smTJ9WsWTOFh4drzJgxKlOmjOLi4jRjxgx7mYyMDLVs2VJvvvmmWrRooUmTJqlVq1YaP368OnTo4NTWV199paefflodO3bUmDFjlJqaqjZt2uTrfbnh4eHauHFjjmXOnTunzz\/\/XHXr1lW5cuWyLNOhQwd5eHg4HZdryc35a3p6upo2baoSJUpozJgxCg8PV3x8vOLj4\/PUliTFxsaqSZMmkmRva86cOXmu507zz7ymALdcamqqOnTooJdfflmS1LdvX91\/\/\/167733nC7B27Nnj3bv3q3SpUtLunyjfa1atTR69GiNGzcu1216e3urbdu2iouLU\/Xq1Z0uBQRw9zl9+rQOHjyomJiYfKuzWrVqki4\/KKpq1ar5Vu\/VduzYoYoVK2Z5CVymGjVqaP369dqzZ4\/uvffeXNfdqlUrvfTSS\/Lz88t2rHR3d9fnn38uNzc3SZdPsF944QUtXbpULVu2zHVb5cuXV926dTVx4kQ1adJE9evXz\/W2wN1k8ODBevTRR1WzZk099NBDqlu3rho1aqQGDRrY\/x1eaf78+fLw8LCPbx07dtTw4cO1YsUKtWrVKse2Dhw4oPPnzzsFsswf52rUqJHttsHBwfLx8dHOnTsdlh86dEhjx47V888\/L+lyWKpVq5aGDh2qzp07y83NTfPmzdPatWu1fv161alTx75ttWrV1LdvX23cuNHhB8edO3dqx44d9tspGjRooBo1amj+\/Pnq379\/jvuYW+XLl9fx48d19OhRBQQEZFlm9+7dunTpUo7HxcPDQxUrVnQ6LteSm\/PX1NRUNW3aVBMnTpQkPf3002rRooVGjx6tgQMHys\/PL9ft1a5dW2FhYVqzZg3nyldgJhZ2ffv2dfhet25d7du3z6lcq1at7AFWkh566CHVqlVLK1asuOl9BHBnO336tCSpcOHC+VZn5r2tZ86cybc6s3LmzJlr9jtzfeZ+5qc+ffo4nDjHxcXJ1dWVsRm4SZo0aaKvv\/5aLVu21LZt2zRmzBhFR0erdOnSWrJkiVP5xMRENW\/e3D4OVKhQQeHh4UpMTLxmW5kzmVffu5k5ruVm7Ll63HF1dVVsbKz9u7u7u2JjY3X06FFt2bJFkrRw4UJVrlxZlSpV0vHjx+2fhg0bSpKSkpIc6mzcuLHD8wCqV68uHx+fLM8nr1fmMTh+\/Hi2ZW7kuOSXK0O7zWZT\/\/79lZaWprVr196U9u42hFhIkjw9PeXv7++wzNfXVydPnnQqW6FCBadlYWFhvIoBwA3LvBwuPwPn2bNnJf3\/ycyxY8d0+PBh+ydz\/Y0qXLjwNfud2xOr63H12FyoUCGVLFmSsRm4iR588EF9\/PHHOnnypL777jsNHTpUZ86cUdu2bR1uYdi5c6e+\/\/57RUREaM+ePfZP\/fr1tWzZslwHqatvD8gcS3Iz9lw97pQqVUre3t4Oy8LCwiTJPm7s3r1bP\/\/8s\/z9\/R0+meWufoBVYGCgU9vZnU9er8xjcPV7Za90I8clPxQoUEDly5d3WHb1scWN4XJiSJLDk+zyg81my\/I+rPT09HxtB8CdxcfHR6VKlcr1PWa5kVlXaGiopMsnnb\/99pt9fXx8fL68f69y5cr6\/vvvdeHChWwvKf7xxx\/l5uZmD5zZnYTd6rGSsRm4Me7u7nrwwQf14IMPKiwsTN27d9fChQvt90DOnTtXkvTcc8\/pueeec9r+o48+Uvfu3bOtv3jx4pLkFAYz71X\/8ccfs932t99+0+nTp1WlSpW87ZQu3xN77733Znu7WNmyZR2+Z3c+mdd783OSeQxyuiQ3NDRUrq6uOR6XCxcu6Ndff9UDDzxgX3Yrz1\/\/KeO\/VRFikWe7d+92WrZr1y4FBwfbv\/v6+mZ56ciVJ45Szr+iAbg7PfbYY5o2bZq+\/vpr1a5d+4bqOnv2rBYvXqyyZcvaT\/YSExMdHqx09a\/l1+uxxx7T119\/rYULF2Z539L+\/fv15ZdfqnHjxvLy8pL0\/5fF\/fXXXw6v6Lh6rJSuPV7u3r1bDRo0sH8\/e\/as\/vjjDzVr1sy+zNfXV3\/99ZfDdmlpafrjjz\/y1BaA7GWGosx\/V8YYzZs3Tw0aNNDTTz\/tVP6VV15RYmJijiE2MDBQXl5eSklJcVgeFhamsLAwffLJJ5owYUKWs4rvv\/++pMtj1JUOHTqkv\/\/+22E2dteuXZJkP6cLCQnRtm3b1KhRo3\/MuJCSkiI\/Pz+nKwiv5O3trQYNGmjdunX67bffFBQU5FTmww8\/1IULFxyOS36dv2ZkZGjfvn322VfJ+dheOf7n1FZu2rsbcTkx8uyTTz7RwYMH7d+\/++47ffvtt3r00Ufty0JCQvTLL7\/o2LFj9mXbtm1TcnKyQ12Z7+y6+h8wgLvXCy+8IG9vb\/Xq1SvLp57v3btXEyZMuGY958+fV+fOnfXnn39q2LBh9pOAiIgINW7c2P7JrxAbGxurgIAADRkyxOkkKDU1Vd27d5cxRsOHD7cvz7x3bMOGDfZlf\/\/9t2bPnu1Uv7e3d45j5bRp03Tx4kX796lTp+rSpUtOY\/OVbWVud\/Uv\/5kntYzNQPaSkpKynLXLvA+9YsWKki6\/r3T\/\/v3q3r272rZt6\/Tp0KGDkpKSdOjQoWzbcnNz0wMPPKDNmzc7rRs+fLhOnjypvn37Ov1b3rJli0aPHq1q1aqpTZs2DusuXbqkd955x\/49LS1N77zzjvz9\/RUeHi5Jat++vQ4ePKjp06c7tXv+\/Hn9\/fff2fb5ZtmyZUuufuB86aWXZIxRt27dnJ4In5KSohdeeEElS5Z0uC84P89fJ0+ebP\/fxhhNnjxZbm5uatSokaTLD99zcXFxGpOnTJniVBdjsjNmYpFnoaGhqlOnjuLi4nThwgW99dZbKl68uF544QV7mR49emjcuHGKjo5Wz549dfToUb399tuqWrWqw30fXl5eqlKlij744AOFhYWpWLFiqlatmv1pogDuPiEhIZo3b546dOigypUrq0uXLqpWrZrS0tK0ceNGLVy4UN26dXPY5uDBg\/bL9c6ePasdO3Zo4cKFOnz4sAYNGuRwkpKTpUuXatu2bZIuv9Lixx9\/1KhRoyRJLVu2VPXq1bPdtnjx4lq0aJGaN2+u+++\/X7169VKVKlV0+PBhzZo1S3v27NGECRMcnuQZFRWlwMBA9ezZU0OGDJGLi4tmzJghf39\/HThwwKH+8PBwTZ06VaNGjVJoaKgCAgLsD1eRLp+ANmrUSO3bt9evv\/6qKVOmqE6dOg5PJu7Vq5f69u2rNm3aqEmTJtq2bZtWr17tdFlezZo15eLiotGjR+vUqVPy8PBQw4YNs30SKHA3GjBggM6dO6fWrVurUqVK9jHqgw8+UHBwsH1mNTExUS4uLmrevHmW9bRs2VLDhg3TggUL7E8KzkpMTIyGDRum06dPO7xO58knn9SmTZs0YcIE7dixQ08++aR8fX21detWzZgxwz42Xf3E5FKlSmn06NHav3+\/wsLC9MEHH+iHH37QtGnT7GU7d+6sDz\/8UH379lVSUpIiIiKUnp6uX375RR9++KFWr17tcDnuzXb06FH9+OOP6tev3zXL1qtXT2+++aaef\/55Va9eXd26dVPJkiX1yy+\/aPr06crIyNCKFSscHpaVX+evnp6eWrVqlbp27apatWpp5cqVWr58uV588UX7DHKRIkXUrl07TZo0STabTSEhIVq2bJnTfcaS7D8qDBw4UNHR0XJxcVHHjh1v6Fha3m16Py1uo6tfMp35UuarXf3i6cyXL7\/xxhtm7NixpmzZssbDw8PUrVvXbNu2zWn7uXPnmvLlyxt3d3dTs2ZNs3r1aoeXRWfauHGjCQ8PN+7u7g4viwZwd9u1a5fp3bu3CQ4ONu7u7qZw4cImIiLCTJo0yaSmptrLBQUF2V\/+brPZjI+Pj6latarp3bu3+fbbb\/PUZnYvldcVL56\/lpSUFNO7d28TGBho3NzcjJ+fn2nZsqX58ssvsyy\/ZcsWU6tWLePu7m4CAwPNuHHj7ON0SkqKvdzhw4dN8+bNTeHChY0kExkZaYz5\/zF9\/fr1pk+fPsbX19cUKlTIPPnkk+bEiRMObaWnp5t\/\/etfxs\/PzxQsWNBER0ebPXv2mKCgINO1a1eHstOnTzfly5c3Li4uRpJJSkrK5VEE7g4rV640PXr0MJUqVTKFChUy7u7uJjQ01AwYMMAcOXLEGGNMWlqaKV68uKlbt26OdZUrV87cd999OZY5cuSIcXV1NXPmzMly\/SeffGKaNGlifH19jYeHhwkNDTWDBg0yx44dcyobGRlpqlatajZv3mxq165tPD09TVBQkJk8ebJT2bS0NDN69GhTtWpV4+HhYXx9fU14eLgZMWKEOXXqlL2cJNOvXz+n7a8eX2bMmGEkma1bt9qXXX3OmdV2xhgzdepUU7BgQXP69Oksj0FWNmzYYGJiYoyfn59xc3MzgYGBpnfv3mb\/\/v1Zlr\/R89fM8+q9e\/eaqKgoU7BgQVOiRAkTHx9v0tPTHeo4duyYadOmjSlYsKDx9fU1sbGxZvv27U7\/n3Pp0iUzYMAA4+\/vb2w2m9OxuhvZjMnHO61xR9u\/f7\/KlSunN954Q4MHD77d3QEASJo1a5a6d++uTZs23dIZEQC3Xs+ePbVr1y59+eWXN1RP\/fr1dfz48Xx9iF5uTZw4Uc8884z27Nnj8Dqeq5UtW1bR0dF699137cvuu+8+1a9fX+PHj78VXb0u3bp106JFi\/LtyffIGpcTAwAAABYQHx+vsLAwJScnKyIi4nZ357ps2rRJ3t7eWT5sKdPFixd14sQJh1sdVq1apd27d2v16tW3opv4hyPEAgAAABYQGBio1NTU292N6\/LRRx\/piy++UGJionr16iVX16xjyOrVq7VgwQKdP3\/e\/hAkSWratCmzm7AjxAIAAAC4qQYPHqwzZ86oZ8+eOV4O\/Prrr2vPnj169dVX1aRJk1vYQ1gJ98QCAAAAACyD98QCAAAAACyDEAsAAAAAsAxCLAAAAADAMnL9YKcmBdrdzH4AuEOtyVh4u7tw0zE+ArgejI8AkLVrjY\/MxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALMNmjDG5KZhxuMLN7guAO1CBe3bf7i7cdIyPAK4H4yMAZO1a4yMzsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAy3DNbcHoUjVvYjcA3KnWZNzuHtx8jI8ArgfjIwBk7VrjIzOxAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLsBljTG4KZhyucLP7AuAOVOCe3be7Czcd4yOA68H4CABZu9b4yEwsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyXHNbMLpUzZvYDeDOsfrQD7e7C7jFGB8Ba2GcvnUYHwFrscr4yEwsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAybMYYc7s7AQAAAABAbjATCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLF3iW7duik4OPi6ty1UqFD+dugfYv\/+\/bLZbHrzzTdzVf7DDz9UsWLFdPbs2ZvcM2d5+TvYbDYlJCTkS7s7duyQq6urtm\/fni\/1AQAAADfipoTYWbNmyWazOXwCAgLUoEEDrVy58obqvrpeb29vValSRaNGjdK5c+euq84VK1ZkecJ\/7tw5JSQk6IsvvrihPt8MX3zxhcNxcHFxUUBAgNq2baudO3felj7l9XhduQ9z587NskxERIRsNpuqVauWjz29Punp6YqPj9eAAQMcwuRnn32mnj17qlq1anJxcbnmjwV79+7VE088oYCAAHl5ealChQoaNmzYTe37xo0blZCQoL\/++ivP21apUkXNmzfX8OHD879jAAAAQB653szKR44cqXLlyskYoyNHjmjWrFlq1qyZli5dqscee+y6623SpIm6dOkiSTp79qy+\/PJLvfzyy9q2bZsWLlyY5\/pWrFih\/\/73v05B9ty5cxoxYoQkqX79+tfd35tp4MCBevDBB3Xx4kX9+OOPevvtt\/XFF19o+\/btuueee+zlpk+froyMjJval+s9Xp6enpo3b56eeuoph+X79+\/Xxo0b5enpmZ\/dvG5Lly7Vr7\/+qj59+jgsnzdvnj744APdf\/\/9KlWqVI51\/PDDD6pfv75Kly6tQYMGqXjx4jpw4IB+\/\/33fO3r+fPn5er6\/\/+8N27cqBEjRqhbt24qWrRonuvr27evmjVrpr179yokJCQfewoAAADkzU0NsY8++qgeeOAB+\/eePXuqRIkSmj9\/\/g2F2LCwMIfA07dvX6Wlpenjjz9WamrqPyb03Ap169ZV27Zt7d8rVqyouLg4vf\/++3rhhRfsy93c3G5H93KlWbNmWrJkiY4fPy4\/Pz\/78nnz5qlEiRKqUKGCTp48eRt7eNnMmTMVERGh0qVLOyz\/z3\/+o+nTp8vNzU2PPfZYtpfdZmRkqHPnzqpUqZKSkpLk5eV10\/qa3\/8GGjduLF9fX82ePVsjR47M17oBAACAvLil98QWLVpUXl5eDjNEkvTHH3\/ol19+0cWLF6+77nvuuUc2m82p7oULFyo8PFxeXl7y8\/PTU089pYMHD9rXd+vWTf\/9738lOV6qvH\/\/fvn7+0uSRowYYV9+5WztunXrVLduXXl7e6to0aKKiYlxupQ3ISFBNptNu3bt0lNPPaUiRYrI399fL7\/8sowx+v333xUTEyMfHx\/dc889Gjt27HUfA+lyqJUuX7J6pazuiT1x4oQ6d+4sHx8fFS1aVF27dtW2bdtks9k0a9Ysp7oPHjyoVq1aqVChQvL399fgwYOVnp4uSbk6XtmJiYmRh4eH0yz6vHnz1L59e7m4uDhtM3PmTDVs2FABAQHy8PBQlSpVNHXqVKdymzdvVnR0tPz8\/OTl5aVy5cqpR48eOfbHGKM+ffrI3d1dH3\/8sSQpNTVVq1atUuPGjZ3KlypVKlc\/Enz22Wfavn274uPj5eXlpXPnztmPX17s27dP0dHR8vb2VqlSpTRy5EgZYxzKXHnsExISNGTIEElSuXLlHP4bl6Q1a9aoTp06Klq0qAoVKqSKFSvqxRdfdKjPzc1N9evX16effprn\/gIAAAD56abOxJ46dUrHjx+XMUZHjx7VpEmTdPbsWafLRocOHarZs2crJSUlVw8fSk1N1fHjxyVJf\/\/9t5KTkzV79mw98cQTDiF21qxZ6t69ux588EG99tprOnLkiCZMmKDk5GR9\/\/33Klq0qGJjY3Xo0CGtWbNGc+bMsW\/r7++vqVOnKi4uTq1bt9bjjz8uSapevbokae3atXr00UdVvnx5JSQk6Pz585o0aZIiIiK0detWp\/3o0KGDKleurNdff13Lly\/XqFGjVKxYMb3zzjtq2LChRo8ercTERA0ePFgPPvig6tWrdz2H3B5MfH19cyyXkZGhFi1a6LvvvlNcXJwqVaqkTz\/9VF27ds2yfHp6uqKjo1WrVi29+eabWrt2rcaOHauQkBDFxcVd83jlpGDBgoqJidH8+fMVFxcnSdq2bZt+\/vlnvfvuu\/rxxx+dtpk6daqqVq2qli1bytXVVUuXLtXTTz+tjIwM9evXT5J09OhRRUVFyd\/fX\/\/+979VtGhR7d+\/3x5Ms9vPHj166IMPPtDixYvVvHlzSdKWLVuUlpam+++\/\/5r7k521a9dKkjw8PPTAAw9oy5Ytcnd3V+vWrTVlyhQVK1bsmnWkp6eradOmevjhhzVmzBitWrVK8fHxunTpUrYzpI8\/\/rh27dql+fPna\/z48fbZbn9\/f\/3888967LHHVL16dY0cOVIeHh7as2ePkpOTneoJDw\/Xp59+qtOnT8vHx+e6jwMAAABwQ8xNMHPmTCPJ6ePh4WFmzZrlVL5r165GkklJSblm3VnVK8m0atXKpKam2sulpaWZgIAAU61aNXP+\/Hn78mXLlhlJZvjw4fZl\/fr1M1kdimPHjhlJJj4+3mldzZo1TUBAgDlx4oR92bZt20yBAgVMly5d7Mvi4+ONJNOnTx\/7skuXLpkyZcoYm81mXn\/9dfvykydPGi8vL9O1a9drHoekpCQjycyYMcMcO3bMHDp0yKxatcqEhoYam81mvvvuO4fyXbt2NUFBQfbvH330kZFk3nrrLfuy9PR007BhQyPJzJw502FbSWbkyJEOdd53330mPDw8V8crp31YuHChWbZsmbHZbObAgQPGGGOGDBliypcvb4wxJjIy0lStWtVh23PnzjnVFx0dbd\/GGGMWL15sJJlNmzZl24eUlBQjybzxxhvm4sWLpkOHDsbLy8usXr3aody7775rJJmffvopx31q3ry5w3G+UsuWLY0kU7x4cfPkk0+aRYsWmZdfftm4urqaRx55xGRkZORYd+bfYcCAAfZlGRkZpnnz5sbd3d0cO3bMvvzqv8Mbb7yR5b+x8ePHG0kO22Zn3rx5RpL59ttvr1kWAAAAuFlu6uXE\/\/3vf7VmzRqtWbNGc+fOVYMGDdSrVy+nmbBZs2bJGJPrV8DExMTY6\/300081dOhQrVq1Sk888YT9ssrNmzfr6NGjevrppx3uD2zevLkqVaqk5cuXX\/d+\/fHHH\/rhhx\/UrVs3h9mz6tWrq0mTJlqxYoXTNr169bL\/bxcXFz3wwAMyxqhnz5725UWLFlXFihW1b9++XPelR48e8vf3V6lSpdS0aVOdOnVKc+bM0YMPPpjjdqtWrZKbm5t69+5tX1agQAH7LGZW+vbt6\/C9bt26eeprTqKiolSsWDEtWLBAxhgtWLBAnTp1yrb8lfeTZs74R0ZGat++fTp16pQk2R9gtGzZsmteqp6WlqZ27dpp2bJlWrFihaKiohzWnzhxQtK1Z7hzkvlangcffFBz585VmzZtNHLkSL3yyivauHGjPv\/881zV079\/f\/v\/ttls6t+\/v9LS0uwzvXmReYw+\/fTTaz74K3PfM6+CAAAAAG6HmxpiH3roITVu3FiNGzfWk08+qeXLl6tKlSr2k+7rVaZMGXu9LVu21H\/+8x+NGjVKH3\/8sZYtWyZJ+u233yRdftDR1SpVqmRffz1yqrty5co6fvy4\/v77b4flgYGBDt+LFCkiT09PhwcZZS6\/8iFGhw8fdvicP3\/eofzw4cO1Zs0aLV68WF26dNGpU6dUoMC1\/6y\/\/fabSpYsqYIFCzosDw0NzbK8p6en\/Z7XTL6+vvn2wCU3Nze1a9dO8+bN04YNG\/T777\/riSeeyLZ8cnKyGjdubL8f2d\/f334fZ2aIjYyMVJs2bTRixAj5+fkpJiZGM2fO1IULF5zqe+211\/TJJ59o0aJFOT5Z2Vx172leZAbvq8N55n5u3LjxmnUUKFBA5cuXd1gWFhYm6f8vJc+LDh06KCIiQr169VKJEiXUsWNHffjhh1kG2sx9t9lseW4HAAAAyC+39MFOBQoUUIMGDfTHH39o9+7d+Vp3o0aNJEkbNmzI13rzS1YPJ8pqmeQYlEqWLOnw+eCDDxzK3nvvvWrcuLFatWql2bNnq2XLlurdu3e+v7Ilu77mpyeeeEI\/\/PCDEhISVKNGDVWpUiXLcnv37lWjRo10\/PhxjRs3TsuXL9eaNWv03HPPSZI9gNlsNi1atEhff\/21+vfvr4MHD6pHjx4KDw+3z4pmynxQ0pgxY5SamurUZvHixSXphkJ75ut3SpQo4bA8ICDghuu+Xl5eXtqwYYPWrl2rzp0768cff1SHDh3UpEkTp4dOZfbv6h9eAAAAgFvploZYSbp06ZIkOYWI\/K43KChIkvTrr786lf3111\/t66XsZ5ayW55T3b\/88ov8\/Pzk7e2dh95nL\/Oy6cxPdHR0juVff\/11paam6tVXX82xXFBQkP744w+dO3fOYfmePXuuu683OkNXp04dBQYG6osvvshxFnbp0qW6cOGClixZotjYWDVr1kyNGzfO9pU1Dz\/8sF599VVt3rxZiYmJ+vnnn7VgwQKnMp988ok2btyodu3a2f97ylSpUiVJUkpKynXvX3h4uCQ5PB1bkg4dOiRJTjPdWcnIyHC6hHvXrl2SlOPl+Dn9bQoUKKBGjRpp3Lhx2rFjh1599VWtW7dOSUlJDuVSUlJUoEAB+8wvAAAAcDvc0hB78eJFffbZZ3J3d1flypXty\/PjFTtLly6VJNWoUUOS9MADDyggIEBvv\/22w+WjK1eu1M6dO+1PnZVkD5x\/\/fWXQ52Zl9pevbxkyZKqWbOmZs+e7bBu+\/bt+uyzz9SsWbPr3o+rZV42nfkpWbJkjuVDQkLUpk0bzZo1S4cPH862XHR0tC5evKjp06fbl2VkZNhfN3Q9sjteuWWz2TRx4kTFx8erc+fO2ZbLnBW+csb61KlTmjlzpkO5kydPOl3+W7NmTUnK8pLixo0ba8GCBVq1apU6d+7scElteHi43N3dtXnz5jzvV6bMVwnNnDnToe53331XktSkSZNc1TN58mT7\/zbGaPLkyXJzc7NfjZCV7P4b\/\/PPP53KZneMtmzZoqpVq6pIkSK56icAAABwM9zUV+ysXLlSv\/zyi6TLrzuZN2+edu\/erX\/\/+98Or+jI6yt2du3apblz50qSzp07p2+++UazZ89WaGioPfy4ublp9OjR6t69uyIjI9WpUyf7K3aCg4Ptl55K\/z9DNnDgQEVHR8vFxUUdO3aUl5eXqlSpog8++EBhYWEqVqyYqlWrpmrVqumNN97Qo48+qtq1a6tnz572V+wUKVIkV+9GvZmGDBmiDz\/8UG+99ZZef\/31LMu0atVKDz30kAYNGqQ9e\/aoUqVKWrJkiT3UXM+sak7HK7diYmIUExOTY5moqCi5u7urRYsWio2N1dmzZzV9+nQFBATojz\/+sJebPXu2pkyZotatWyskJERnzpzR9OnT5ePjk+0PDa1atdLMmTPVpUsX+fj46J133pF0+Z7gqKgorV271ulVNj\/++KOWLFki6fJM9qlTpzRq1ChJl39UadGihaTL7zIeNmyYhg8frqZNm6pVq1batm2bpk+frk6dOl3zYVyZ\/Vi1apW6du2qWrVqaeXKlVq+fLlefPHFHGdyM\/8bHzZsmDp27Cg3Nze1aNFCI0eO1IYNG9S8eXMFBQXp6NGjmjJlisqUKaM6derYt7948aLWr1+vp59++pp9BAAAAG6qm\/HI46xesePp6Wlq1qxppk6d6vQqkRt5xY6Li4spU6aM6dOnjzly5IhT+Q8++MDcd999xsPDwxQrVsw8+eST5n\/\/+59DmUuXLpkBAwYYf39\/Y7PZHF63s3HjRhMeHm7c3d2dXluydu1aExERYby8vIyPj49p0aKF2bFjh0Pdma\/YufoVJl27djXe3t5O\/c3qdTJZufL1NFmpX7++8fHxMX\/99Ze9vatf\/XLs2DHzxBNPmMKFC5siRYqYbt26meTkZCPJLFiw4Jp9zdy3K+V0vPK6D5myOiZLliwx1atXN56eniY4ONiMHj3azJgxw+G\/o61bt5pOnTqZwMBA4+HhYQICAsxjjz1mNm\/ebK\/nylfsXGnKlClGkhk8eLB92ccff+zwGqBM2b1SSpLT65IyMjLMpEmTTFhYmHFzczNly5Y1L730kklLS8vxGBjz\/3+HvXv3mqioKFOwYEFTokQJEx8fb9LT0x3KZnXsX3nlFVO6dGlToEAB+3H6\/PPPTUxMjClVqpRxd3c3pUqVMp06dTK7du1y2HblypVGktm9e\/c1+wkAAADcTDZjbuBxq7jjfPLJJ2rdurW++uorRURE3O7u\/KOkp6erSpUqat++vV555ZXb3Z1bqlWrVrLZbFq8ePHt7goAAADucoTYu9j58+cdHoaUnp6uqKgobd68WYcPH872QUl3sw8++EBxcXE6cOCAChUqdLu7c0vs3LlT9957r3744Yc8XRoOAAAA3AyE2LtYr169dP78edWuXVsXLlzQxx9\/rI0bN+o\/\/\/mPhg4deru7BwAAAABOCLF3sXnz5mns2LHas2ePUlNTFRoaqri4OPXv3\/92dw0AAAAAskSIBQAAAABYxi19TywAAAAAADeCEAsAAAAAsAxCLAAAAGABv\/\/+uzw9PZWcnHy7u5KvEhISZLPZHJYFBwerW7du9u+rVq1SoUKFdOzYsVvcO\/wTEWLvQrNmzZLNZtPmzZtvd1d07tw5JSQk6IsvvrjdXQHwD7N3717FxsaqfPny8vT0lI+PjyIiIjRhwgSdP3\/eXi44OFg2m002m00FChRQ0aJFde+996pPnz769ttv89Tm1KlT1a5dOwUGBspmszmcQOXWgQMH1LdvXwUHB8vDw0MBAQFq1arVDZ90TpkyRbNmzbqhOnJrx44dSkhI0P79+29Je4BV\/fTTT2rbtq2CgoLk6emp0qVLq0mTJpo0aVK227Rv3142m03\/+te\/8tzeyJEjVatWLUVERDitW7ZsmZo2barixYvL09NTYWFhGjx4sE6cOJHndm6m6z0Pbdq0qUJDQ\/Xaa6\/labvk5GS1bt1aJUqUkIeHh4KDgxUbG6sDBw7kqZ4r3erz1xUrVighIeGWtGUZBnedmTNnGklm06ZNt7sr5tixY0aSiY+Pv91dAfAPsmzZMuPl5WWKFi1qBg4caKZNm2YmT55sOnbsaNzc3Ezv3r3tZYOCgkzNmjXNnDlzzJw5c8yUKVPMgAEDzD333GMkmeeeey7X7QYFBZlixYqZpk2bGldXV9O1a9c89furr74yPj4+xsfHxzz\/\/PPm3XffNaNGjTKhoaHGZrOZiRMn5qm+K1WtWtVERkZe9\/Z5sXDhQiPJJCUl3ZL2ACtKTk427u7uJjQ01Lzyyitm+vTpZvjw4SYqKsqEhIRkuc2pU6eMp6enCQ4ONmXLljUZGRm5bu\/o0aPGzc3NzJs3z2ndoEGDjCRTo0YNM3r0aDN9+nQTFxdnPDw8TOnSpc0vv\/xy3fuZ37I6D7148aI5f\/68Q7nU1FSTlpbmsGzKlCmmYMGC5vTp07lqa+LEicZms5mQkBDzyiuvmHfffdcMGjTIFClSxBQpUsQkJydf1z7c6vPXfv36GWKbI9fbF58BAHCWkpKijh07KigoSOvWrVPJkiXt6\/r166c9e\/Zo+fLlDtuULl1aTz31lMOy0aNH64knntD48eNVoUIFxcXFXbPt9evX22dhCxUqlKd+nzx5Um3btpWXl5eSk5MVEhJiX\/f8888rOjpazz77rMLDw\/XII4\/kqW4A\/zyvvvqqihQpok2bNqlo0aIO644ePZrlNh999JHS09M1Y8YMNWzYUBs2bFBkZGSu2ps7d65cXV3VokULh+Xz58\/X2LFj1aFDByUmJsrFxcW+rlu3bmrQoIHatWunrVu3ytX1n3nq7+rq6tQ3Dw8Pp3Jt2rTRgAEDtHDhQvXo0SPHOpOTk\/Xss8+qTp06WrVqlQoWLGhfFxcXp4iICLVt21Y\/\/\/yzfH1982dHcOvc7hSNW+\/qX8C6du1qvL29zf\/+9z8TExNjvL29jZ+fnxk0aJC5dOmSfbuUlBQjybzxxhtm3LhxJjAw0Hh6epp69eqZn376yaGNyMjILGcMunbtaoKCghzqu\/rDrCxwd+vbt6+RlOtfyIOCgkzz5s2zXHfmzBlTrFgxU7p06TzNeBhjjLe3d55mYl977TUjybz\/\/vtZrt+3b59xcXEx0dHR9mXx8fFZ\/rqeOU6npKQYYy7v49VjZeYYm1l2\/fr1pk+fPqZYsWKmcOHCpnPnzubPP\/90qDe7MTYoKMi+r5n1Xf1hVhZwVLFiRVO\/fv08bdOoUSPTrFkzY4wxlStXdriq5Frq1auXZXsVK1Y0vr6+5tSpU1luN2LECCPJzJ8\/374sMjLSVK1a1WzevNnUrl3bPjs8depUp+1TU1PN8OHDTUhIiHF3dzdlypQxQ4YMMampqQ7lJJl+\/fqZxYsXm6pVqxp3d3dTpUoVs3LlSodyWc3EZjUWXjkuXem+++4zLVu2zHJfrxQdHW1cXFzMvn37slw\/e\/ZsI8m89tprDsflRs9fM8+r9+7da6KiokzBggVNyZIlzYgRIxz+fygpKSnLsTWz\/pkzZ9rry6q9ux33xEKSlJ6erujoaBUvXlxvvvmmIiMjNXbsWE2bNs2p7Pvvv6+JEyeqX79+Gjp0qLZv366GDRvqyJEjeWrT399fU6dOlSS1bt1ac+bM0Zw5c\/T444\/nyz4BsKalS5eqfPny+TJbWahQIbVu3VoHDx7Ujh078qF32Vu6dKk8PT3Vvn37LNeXK1dOderU0bp16xzu6c2Nt956S2XKlFGlSpXsY+WwYcMcyvTv3187d+5UQkKCunTposTERLVq1Uomj6+Dr1evngYOHChJevHFF+3tVa5cOU\/1AHe6oKAgbdmyRdu3b89V+UOHDikpKUmdOnWSJHXq1EmLFi1SWlraNbe9ePGiNm3apPvvv99h+e7du\/Xrr78qJiZGPj4+WW7bpUsXSZfvmb3SyZMn1axZM4WHh2vMmDEqU6aM4uLiNGPGDHuZjIwMtWzZUm+++aZatGihSZMmqVWrVho\/frw6dOjg1NZXX32lp59+Wh07dtSYMWOUmpqqNm3a5Ot9ueHh4dq4cWOOZc6dO6fPP\/9cdevWVbly5bIs06FDB3l4eDgdl2vJzflrenq6mjZtqhIlSmjMmDEKDw9XfHy84uPj89SWJMXGxqpJkyaSZG9rzpw5ea7nTvPPvKYAt1xqaqo6dOigl19+WZLUt29f3X\/\/\/XrvvfecLsHbs2ePdu\/erdKlS0u6fKN9rVq1NHr0aI0bNy7XbXp7e6tt27aKi4tT9erVnS4FBHD3OX36tA4ePKiYmJh8q7NatWqSLj8oqmrVqvlW79V27NihihUrZnkJXKYaNWpo\/fr12rNnj+69995c192qVSu99NJL8vPzy3asdHd31+effy43NzdJl0+wX3jhBS1dulQtW7bMdVvly5dX3bp1NXHiRDVp0kT169fP9bbA3WTw4MF69NFHVbNmTT300EOqW7euGjVqpAYNGtj\/HV5p\/vz58vDwsI9vHTt21PDhw7VixQq1atUqx7YOHDig8+fPOwWyzB\/natSoke22wcHB8vHx0c6dOx2WHzp0SGPHjtXzzz8v6XJYqlWrloYOHarOnTvLzc1N8+bN09q1a7V+\/XrVqVPHvm21atXUt29fbdy40eEHx507d2rHjh322ykaNGigGjVqaP78+erfv3+O+5hb5cuX1\/Hjx3X06FEFBARkWWb37t26dOlSjsfFw8NDFStWdDou15Kb89fU1FQ1bdpUEydOlCQ9\/fTTatGihUaPHq2BAwfKz88v1+3Vrl1bYWFhWrNmDefKV2AmFnZ9+\/Z1+F63bl3t27fPqVyrVq3sAVaSHnroIdWqVUsrVqy46X0EcGc7ffq0JKlw4cL5Vmfmva1nzpzJtzqzcubMmWv2O3N95n7mpz59+jicOMfFxcnV1ZWxGbhJmjRpoq+\/\/lotW7bUtm3bNGbMGEVHR6t06dJasmSJU\/nExEQ1b97cPg5UqFBB4eHhSkxMvGZbmTOZV9+7mTmu5WbsuXrccXV1VWxsrP27u7u7YmNjdfToUW3ZskWStHDhQlWuXFmVKlXS8ePH7Z+GDRtKkpKSkhzqbNy4scPzAKpXry4fH58szyevV+YxOH78eLZlbuS45JcrQ7vNZlP\/\/v2VlpamtWvX3pT27jaEWEiSPD095e\/v77DM19dXJ0+edCpboUIFp2VhYWG8igHADcu8HC4\/A+fZs2cl\/f\/JzLFjx3T48GH7J3P9jSpcuPA1+53bE6vrcfXYXKhQIZUsWZKxGbiJHnzwQX388cc6efKkvvvuOw0dOlRnzpxR27ZtHW5h2Llzp77\/\/ntFRERoz5499k\/9+vW1bNmyXAepq28PyBxLcjP2XD3ulCpVSt7e3g7LwsLCJMk+buzevVs\/\/\/yz\/P39HT6Z5a5+gFVgYKBT29mdT16vzGNw9Xtlr3QjxyU\/FChQQOXLl3dYdvWxxY3hcmJIksOT7PKDzWbL8j6s9PT0fG0HwJ3Fx8dHpUqVyvU9ZrmRWVdoaKikyyedv\/32m319fHx8vrx\/r3Llyvr+++914cKFbC8p\/vHHH+Xm5mYPnNmdhN3qsZKxGbgx7u7uevDBB\/Xggw8qLCxM3bt318KFC+33QM6dO1eS9Nxzz+m5555z2v6jjz5S9+7ds62\/ePHikuQUBjPvVf\/xxx+z3fa3337T6dOnVaVKlbztlC7fE3vvvfdme7tY2bJlHb5ndz6Z13vzc5J5DHK6JDc0NFSurq45HpcLFy7o119\/1QMPPGBfdivPX\/8p479VEWKRZ7t373ZatmvXLgUHB9u\/+\/r6ZnnpyJUnjlLOv6IBuDs99thjmjZtmr7++mvVrl37huo6e\/asFi9erLJly9pP9hITEx0erHT1r+XX67HHHtPXX3+thQsXZnnf0v79+\/Xll1+qcePG8vLykvT\/l8X99ddfDq\/ouHqslK49Xu7evVsNGjSwfz979qz++OMPNWvWzL7M19dXf\/31l8N2aWlp+uOPP\/LUFoDsZYaizH9XxhjNmzdPDRo00NNPP+1U\/pVXXlFiYmKOITYwMFBeXl5KSUlxWB4WFqawsDB98sknmjBhQpaziu+\/\/76ky2PUlQ4dOqS\/\/\/7bYTZ2165dkmQ\/pwsJCdG2bdvUqFGjf8y4kJKSIj8\/P6crCK\/k7e2tBg0aaN26dfrtt98UFBTkVObDDz\/UhQsXHI5Lfp2\/ZmRkaN++ffbZV8n52F45\/ufUVm7auxtxOTHy7JNPPtHBgwft37\/77jt9++23evTRR+3LQkJC9Msvv+jYsWP2Zdu2bVNycrJDXZnv7Lr6HzCAu9cLL7wgb29v9erVK8unnu\/du1cTJky4Zj3nz59X586d9eeff2rYsGH2k4CIiAg1btzY\/smvEBsbG6uAgAANGTLE6SQoNTVV3bt3lzFGw4cPty\/PvHdsw4YN9mV\/\/\/23Zs+e7VS\/t7d3jmPltGnTdPHiRfv3qVOn6tKlS05j85VtZW539S\/\/mSe1jM1A9pKSkrKctcu8D71ixYqSLr+vdP\/+\/erevbvatm3r9OnQoYOSkpJ06NChbNtyc3PTAw88oM2bNzutGz58uE6ePKm+ffs6\/VvesmWLRo8erWrVqqlNmzYO6y5duqR33nnH\/j0tLU3vvPOO\/P39FR4eLklq3769Dh48qOnTpzu1e\/78ef3999\/Z9vlm2bJlS65+4HzppZdkjFG3bt2cngifkpKiF154QSVLlnS4Lzg\/z18nT55s\/9\/GGE2ePFlubm5q1KiRpMsP33NxcXEak6dMmeJUF2OyM2ZikWehoaGqU6eO4uLidOHCBb311lsqXry4XnjhBXuZHj16aNy4cYqOjlbPnj119OhRvf3226patarDfR9eXl6qUqWKPvjgA4WFhalYsWKqVq2a\/WmiAO4+ISEhmjdvnjp06KDKlSurS5cuqlatmtLS0rRx40YtXLhQ3bp1c9jm4MGD9sv1zp49qx07dmjhwoU6fPiwBg0a5HCSkpOlS5dq27Ztki6\/0uLHH3\/UqFGjJEktW7ZU9erVs922ePHiWrRokZo3b677779fvXr1UpUqVXT48GHNmjVLe\/bs0YQJExye5BkVFaXAwED17NlTQ4YMkYuLi2bMmCF\/f38dOHDAof7w8HBNnTpVo0aNUmhoqAICAuwPV5Eun4A2atRI7du316+\/\/qopU6aoTp06Dk8m7tWrl\/r27as2bdqoSZMm2rZtm1avXu10WV7NmjXl4uKi0aNH69SpU\/Lw8FDDhg2zfRIocDcaMGCAzp07p9atW6tSpUr2MeqDDz5QcHCwfWY1MTFRLi4uat68eZb1tGzZUsOGDdOCBQvsTwrOSkxMjIYNG6bTp087vE7nySef1KZNmzRhwgTt2LFDTz75pHx9fbV161bNmDHDPjZd\/cTkUqVKafTo0dq\/f7\/CwsL0wQcf6IcfftC0adPsZTt37qwPP\/xQffv2VVJSkiIiIpSenq5ffvlFH374oVavXu1wOe7NdvToUf3444\/q16\/fNcvWq1dPb775pp5\/\/nlVr15d3bp1U8mSJfXLL79o+vTpysjI0IoVKxwelpVf56+enp5atWqVunbtqlq1amnlypVavny5XnzxRfsMcpEiRdSuXTtNmjRJNptNISEhWrZsmdN9xpLsPyoMHDhQ0dHRcnFxUceOHW\/oWFrebXo\/LW6jq18ynflS5qtd\/eLpzJcvv\/HGG2bs2LGmbNmyxsPDw9StW9ds27bNafu5c+ea8uXLG3d3d1OzZk2zevVqh5dFZ9q4caMJDw837u7uDi+LBnB327Vrl+ndu7cJDg427u7upnDhwiYiIsJMmjTJpKam2ssFBQXZX\/5us9mMj4+PqVq1qundu7f59ttv89Rmdi+V1xUvnr+WlJQU07t3bxMYGGjc3NyMn5+fadmypfnyyy+zLL9lyxZTq1Yt4+7ubgIDA824cePs43RKSoq93OHDh03z5s1N4cKFjSQTGRlpjPn\/MX39+vWmT58+xtfX1xQqVMg8+eST5sSJEw5tpaenm3\/961\/Gz8\/PFCxY0ERHR5s9e\/aYoKAg07VrV4ey06dPN+XLlzcuLi5GkklKSsrlUQTuDitXrjQ9evQwlSpVMoUKFTLu7u4mNDTUDBgwwBw5csQYY0xaWpopXry4qVu3bo51lStXztx33305ljly5IhxdXU1c+bMyXL9J598Ypo0aWJ8fX2Nh4eHCQ0NNYMGDTLHjh1zKhsZGWmqVq1qNm\/ebGrXrm08PT1NUFCQmTx5slPZtLQ0M3r0aFO1alXj4eFhfH19TXh4uBkxYoQ5deqUvZwk069fP6ftrx5fZsyYYSSZrVu32pddfc6Z1XbGGDN16lRTsGBBc\/r06SyPQVY2bNhgYmJijJ+fn3FzczOBgYGmd+\/eZv\/+\/VmWv9Hz18zz6r1795qoqChTsGBBU6JECRMfH2\/S09Md6jh27Jhp06aNKViwoPH19TWxsbFm+\/btTv+fc+nSJTNgwADj7+9vbDab07G6G9mMycc7rXFH279\/v8qVK6c33nhDgwcPvt3dAQBImjVrlrp3765Nmzbd0hkRALdez549tWvXLn355Zc3VE\/9+vV1\/PjxfH2IXm5NnDhRzzzzjPbs2ePwOp6rlS1bVtHR0Xr33Xfty+677z7Vr19f48ePvxVdvS7dunXTokWL8u3J98galxMDAAAAFhAfH6+wsDAlJycrIiLidnfnumzatEne3t5ZPmwp08WLF3XixAmHWx1WrVql3bt3a\/Xq1beim\/iHI8QCAAAAFhAYGKjU1NTb3Y3r8tFHH+mLL75QYmKievXqJVfXrGPI6tWrtWDBAp0\/f97+ECRJatq0KbObsCPEAgAAALipBg8erDNnzqhnz545Xg78+uuva8+ePXr11VfVpEmTW9hDWAn3xAIAAAAALIP3xAIAAAAALIMQCwAAAACwDEIsAAAAAMAycv1gpyYF2t3MfgC4Q63JWHi7u3DTMT4CuB6MjwCQtWuNj8zEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAM19wWXH3oh5vYDeDOEV2q5u3uAm4xxkcAyBrjI4CbgZlYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBlEGIBAAAAAJZBiAUAAAAAWAYhFgAAAABgGYRYAAAAAIBluOa2YHSpmjexG8CNW33oh9vdhX8Ujsetw\/gI4HqsybjdPbj5GB8BXI9rjY\/MxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALIMQCwAAAACwDEIsAAAAAMAyCLEAAAAAAMsgxAIAAAAALMNmjDG5KZhxuMLN7gtwR4guVfN2d+EfZU3GwtvdhZuO8RHA9Shwz+7b3YWbjvERwPW41vjITCwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDIIsQAAAAAAyyDEAgAAAAAsgxALAAAAALAMQiwAAAAAwDJcc1swulTNm9gNWNnqQz\/c7i4gC\/xdbh3GR8BaGB9vHcZHwFqsMj4yEwsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAybMcbc7k4AAAAAAJAbzMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxCLAAAAADAMgixAAAAAADLIMQCAAAAACyDEAsAAAAAsAxC7D9U\/fr1Vb9+ffv3\/fv3y2azadasWbetT926dVNwcPBNbeP333+Xp6enkpOTb2o7WUlISJDNZtPx48evWTY4OFjdunXLl3ZPnDghb29vrVixIl\/qAwAAAO5kd22I3bt3r2JjY1W+fHl5enrKx8dHERERmjBhgs6fP39ddQYHB8tms2X5SU1Nzec9yNoXX3xhb3PLli1O67t166ZChQrdkr5cj5EjR6pWrVqKiIhwWvfBBx+odu3a8vb2VtGiRfXII49o3bp12db11Vdf2Y9FboLpjdixY4cSEhK0f\/\/+PG9bvHhx9erVSy+\/\/HL+dwwAAAC4w7je7g7cDsuXL1e7du3k4eGhLl26qFq1akpLS9NXX32lIUOG6Oeff9a0adOuq+6aNWtq0KBBTsvd3d1vtNt5lpCQoKVLl+ZbfdOnT1dGRka+1Xe1Y8eOafbs2Zo9e7bTuoSEBI0cOVJt27ZVt27ddPHiRW3fvl0HDx7Msq6MjAwNGDBA3t7e+vvvv\/O9r7\/++qsKFPj\/34B27NihESNGqH79+tc1W923b19NnDhR69atU8OGDfOxpwAAAMCd5a4LsSkpKerYsaOCgoK0bt06lSxZ0r6uX79+2rNnj5YvX37d9ZcuXVpPPfVUfnT1htSsWVPLli3T1q1bdf\/99+dLnW5ubvlST3bmzp0rV1dXtWjRwmH5N998o5EjR2rs2LF67rnnclXXtGnT9Pvvv6tXr16aMGFCvvfVw8MjX+urXLmyqlWrplmzZhFiAQAAgBzcdZcTjxkzRmfPntV7773nEGAzhYaG6plnnrF\/P378uH755RedO3fuhtvOvOfyarNmzZLNZruuS1GzM2DAAPn6+iohISFX5adMmaKqVavKw8NDpUqVUr9+\/fTXX385lMnqntgFCxYoPDxchQsXlo+Pj+69916n0PjXX3\/p2WefVdmyZeXh4aHQ0FCNHj3aaVb3k08+Ua1atZwud37rrbd0zz336JlnnpExRmfPns1xX\/7880+99NJLGjlypIoWLZqr\/b\/S8ePH1b59e\/n4+Kh48eJ65plnnC4Hv\/Ke2FmzZqldu3aSpAYNGtgvYf7iiy8kSZs3b1Z0dLT8\/Pzk5eWlcuXKqUePHk7tNmnSREuXLpUxJs99BgAAAO4Wd12IXbp0qcqXL69HHnkkV+UnT56sypUr67vvvstV+YsXL+r48eMOn\/wIwHnl4+Oj5557TkuXLtXWrVtzLJuQkKB+\/fqpVKlSGjt2rNq0aaN33nlHUVFRunjxYrbbrVmzRp06dZKvr69Gjx6t119\/XfXr13d4KNO5c+cUGRmpuXPnqkuXLpo4caIiIiI0dOhQPf\/88\/ZyFy9e1KZNm7KcNf7888\/14IMPauLEifL391fhwoVVsmRJTZ48Oct+vfzyy7rnnnsUGxt7rcOUpfbt2ys1NVWvvfaamjVrpokTJ6pPnz7Zlq9Xr54GDhwoSXrxxRc1Z84czZkzR5UrV9bRo0cVFRWl\/fv369\/\/\/rcmTZqkJ598Ut98841TPeHh4frrr7\/0888\/X1e\/AQAAgLvBXXU58enTp3Xw4EHFxMTctDY+++wz+fv7OyyLj4\/P9Yxofho4cKDGjx+vESNG6NNPP82yzLFjx\/Taa68pKipKK1eutN\/nWalSJfXv319z585V9+7ds9x2+fLl8vHx0erVq+Xi4pJlmXHjxmnv3r36\/vvvVaFCBUlSbGysSpUqpTfeeEODBg1S2bJldeDAAZ0\/f17lypVz2P7kyZM6fvy4kpOTtW7dOsXHxyswMFAzZ87UgAED5Obm5hBWf\/zxR73zzjtasWJFtn26lnLlytmPV79+\/eTj46MpU6Zo8ODBql69ulP58uXLq27dupo4caKaNGni8FTpTz75RCdPntRnn32mBx54wL581KhRWdYjXb6\/tlq1atfVdwAAAOBOd1fNxJ4+fVqSVLhw4Vxvk5CQIGOMQzDJSa1atbRmzRqHT5cuXa6nuzesSJEievbZZ7VkyRJ9\/\/33WZZZu3at0tLS9Oyzzzo8qKh3797y8fHJ8f7gokWL6u+\/\/9aaNWuyLbNw4ULVrVtXvr6+DrPTjRs3Vnp6ujZs2CDp8mtmJMnX19dh+8xLh0+cOKF3331XgwcPVvv27bV8+XJVqVLFKQwOHDhQjz76qKKionI4Mjnr16+fw\/cBAwZI0nW9AifzcuZly5blOKst\/f++3+wnKQMAAABWdleFWB8fH0nSmTNnblobfn5+aty4scMnc4btdnjmmWdUtGjRbGeCf\/vtN0lSxYoVHZa7u7urfPny9vVZefrppxUWFqZHH31UZcqUUY8ePbRq1SqHMrt379aqVavk7+\/v8GncuLEk6ejRow7lr74f1MvLS9Llh0q1bdvWvrxAgQLq0KGD\/ve\/\/+nAgQOSLr+CZ+PGjRo7dmy2fc6NzBnjTCEhISpQoMB13bMcGRmpNm3aaMSIEfLz81NMTIxmzpypCxcuOJXN3Pes7psGAAAAcNlddTmxj4+PSpUqpe3bt9+W9rMLJ+np6TetzczZ2ISEhGxnY69XQECAfvjhB61evVorV67UypUrNXPmTHXp0sX+mpyMjAw1adJEL7zwQpZ1hIWFSbr8rlTp8uXDVypWrJg8PT1VtGhRp8uDAwIC7NsEBgZqyJAhateundzd3e2BM\/PhVL\/\/\/rvS0tJUqlSpPO\/njYRKm82mRYsW6ZtvvtHSpUu1evVq9ejRQ2PHjtU333zj8BCrzH338\/O77vYAAACAO91dNRMrSY899pj27t2rr7\/++pa3nXm56NVP\/c1ptjM\/PPvssypatKhGjBjhtC4oKEjS5feeXiktLU0pKSn29dlxd3dXixYtNGXKFO3du1exsbF6\/\/33tWfPHkmXZzHPnj3rNDud+QkMDJQkBQYGysvLSykpKQ71FyhQQDVr1tSxY8eUlpbmsO7QoUOSZL8H+ffff9e8efNUrlw5+yfzScn333+\/mjVrlqvjtXv3bofve\/bsUUZGRo7vf71W0H344Yf16quvavPmzUpMTNTPP\/+sBQsWOJTJ3PfKlSvnqp8AAADA3eiuC7EvvPCCvL291atXLx05csRp\/d69ex1eEZOfr9gJCQmRJPt9oJL0999\/22ctb5bM2dhPP\/1UP\/zwg8O6xo0by93dXRMnTnS4lPe9997TqVOn1Lx582zrzbyPNVOBAgXsDz7KvFy2ffv2+vrrr7V69Wqn7f\/66y9dunRJ0uXLhR944AFt3rzZqVyHDh2Unp7ucJxSU1OVmJioKlWq2GdXFy9e7PTp0KGDJOn999\/X+PHjs92XK\/33v\/91+D5p0iRJ0qOPPprtNt7e3vZ9utLJkyedLpGuWbOmJDldUrxlyxYVKVJEVatWzVU\/AQAAgLvRXXU5sXQ5SM6bN08dOnRQ5cqV1aVLF1WrVk1paWnauHGjFi5caH\/\/p3T5FTsjRoxQUlJSrh\/ulJ2oqCgFBgaqZ8+eGjJkiFxcXDRjxgz5+\/vb7+u8WZ555hmNHz9e27Ztswcu6fIs5tChQzVixAg1bdpULVu21K+\/\/qopU6bowQcf1FNPPZVtnb169dKff\/6phg0bqkyZMvrtt980adIk1axZ0z6bOGTIEC1ZskSPPfaYunXrpvDwcP3999\/66aeftGjRIu3fv99++WxMTIyGDRum06dP2+9fli4\/zfjdd99Vv379tGvXLgUGBmrOnDn67bfftHTpUnu5Vq1aOfUxM7Q\/+uijub5MNyUlRS1btlTTpk319ddfa+7cuXriiSdUo0aNbLepWbOmXFxcNHr0aJ06dUoeHh5q2LCh5s2bpylTpqh169YKCQnRmTNnNH36dPn4+DjNDK9Zs0YtWrTgnlgAAAAgJ+YutWvXLtO7d28THBxs3N3dTeHChU1ERISZNGmSSU1NtZeLj483kkxSUtI16wwKCjLNmzfPscyWLVtMrVq1jLu7uwkMDDTjxo0zM2fONJJMSkqKvVxkZKSJjIy0f09JSTGSzMyZM3OsPykpyUgyCxcudFqXuS\/e3t5O6yZPnmwqVapk3NzcTIkSJUxcXJw5efKkQ5muXbuaoKAg+\/dFixaZqKgoExAQYN+f2NhY88cffzhsd+bMGTN06FATGhpq3N3djZ+fn3nkkUfMm2++adLS0uzljhw5YlxdXc2cOXOc+nfkyBHTtWtXU6xYMePh4WFq1aplVq1aleOxuHKfjx07luuyO3bsMG3btjWFCxc2vr6+pn\/\/\/ub8+fMOZYOCgkzXrl0dlk2fPt2UL1\/euLi42P+b2bp1q+nUqZMJDAw0Hh4eJiAgwDz22GNm8+bNDtvu3LnTSDJr1669Zj8BAACAu5nNmKuudQRuo549e2rXrl368ssvb3dXbqlnn31WGzZs0JYtW5iJBQAAAHJAiMU\/yoEDBxQWFqbPP\/9cERERt7s7t8SJEycUFBSkDz\/8MNcPnwIAAADuVoRYAAAAAIBl3HVPJwYAAAAAWBchFgAAAABgGYRYAAAAAIBlEGIBAAAAC\/j999\/l6emp5OTk292VfJWQkOD0dobg4GB169bN\/n3VqlUqVKiQjh07dot7h38iQuxdaNasWbLZbNq8efPt7orOnTunhIQEffHFF7e7KwD+Yfbu3avY2FiVL19enp6e8vHxUUREhCZMmKDz58\/bywUHB8tms8lms6lAgQIqWrSo7r33XvXp00fffvttntqcOnWq2rVrp8DAQNlsNocTqNw6cOCA+vbtq+DgYHl4eCggIECtWrW64ZPOKVOmaNasWTdUR27t2LFDCQkJ2r9\/\/y1pD7Cqn376SW3btlVQUJA8PT1VunRpNWnSRJMmTcp2m\/bt28tms+lf\/\/pXntsbOXKkatWqleUbHJYtW6amTZuqePHi8vT0VFhYmAYPHqwTJ07kuZ2b6XrPQ5s2barQ0FC99tpredouOTlZrVu3VokSJeTh4aHg4GDFxsbqwIEDearnSrf6\/HXFihVKSEi4JW1Zxu18SS1uj5kzZxpJZtOmTbe7K+bYsWNGkomPj7\/dXQHwD7Js2TLj5eVlihYtagYOHGimTZtmJk+ebDp27Gjc3NxM79697WWDgoJMzZo1zZw5c8ycOXPMlClTzIABA8w999xjJJnnnnsu1+0GBQWZYsWKmaZNmxpXV1fTtWvXPPX7q6++Mj4+PsbHx8c8\/\/zz5t133zWjRo0yoaGhxmazmYkTJ+apvitVrVrVREZGXvf2ebFw4UIjySQlJd2S9gArSk5ONu7u7iY0NNS88sorZvr06Wb48OEmKirKhISEZLnNqVOnjKenpwkODjZly5Y1GRkZuW7v6NGjxs3NzcybN89p3aBBg4wkU6NGDTN69Ggzffp0ExcXZzw8PEzp0qXNL7\/8ct37md+yOg+9ePGiOX\/+vEO51NRUk5aW5rBsypQppmDBgub06dO5amvixInGZrOZkJAQ88orr5h3333XDBo0yBQpUsQUKVLEJCcnX9c+3Orz1379+hlimyPX2xefAQBwlpKSoo4dOyooKEjr1q1TyZIl7ev69eunPXv2aPny5Q7blC5dWk899ZTDstGjR+uJJ57Q+PHjVaFCBcXFxV2z7fXr19tnYQsVKpSnfp88eVJt27aVl5eXkpOTFRISYl\/3\/PPPKzo6Ws8++6zCw8P1yCOP5KluAP88r776qooUKaJNmzapaNGiDuuOHj2a5TYfffSR0tPTNWPGDDVs2FAbNmxQZGRkrtqbO3euXF1d1aJFC4fl8+fP19ixY9WhQwclJibKxcXFvq5bt25q0KCB2rVrp61bt8rV9Z956u\/q6urUNw8PD6dybdq00YABA7Rw4UL16NEjxzqTk5P17LPPqk6dOlq1apUKFixoXxcXF6eIiAi1bdtWP\/\/8s3x9ffNnR3Dr3O4UjVvv6l\/Aunbtary9vc3\/\/vc\/ExMTY7y9vY2fn58ZNGiQuXTpkn27lJQUI8m88cYbZty4cSYwMNB4enqaevXqmZ9++smhjcjIyCxnDLp27WqCgoIc6rv6w6wscHfr27evkZTrX8iDgoJM8+bNs1x35swZU6xYMVO6dOk8zXgYY4y3t3eeZmJfe+01I8m8\/\/77Wa7ft2+fcXFxMdHR0fZl8fHxWf66njlOp6SkGGMu7+PVY2XmGJtZdv369aZPnz6mWLFipnDhwqZz587mzz\/\/dKg3uzE2KCjIvq+Z9V39YVYWcFSxYkVTv379PG3TqFEj06xZM2OMMZUrV3a4quRa6tWrl2V7FStWNL6+vubUqVNZbjdixAgjycyfP9++LDIy0lStWtVs3rzZ1K5d2z47PHXqVKftU1NTzfDhw01ISIhxd3c3ZcqUMUOGDDGpqakO5SSZfv36mcWLF5uqVasad3d3U6VKFbNy5UqHclnNxGY1Fl45Ll3pvvvuMy1btsxyX68UHR1tXFxczL59+7JcP3v2bCPJvPbaaw7H5UbPXzPPq\/fu3WuioqJMwYIFTcmSJc2IESMc\/n8oKSkpy7E1s\/6ZM2fa68uqvbsd98RCkpSenq7o6GgVL15cb775piIjIzV27FhNmzbNqez777+viRMnql+\/fho6dKi2b9+uhg0b6siRI3lq09\/fX1OnTpUktW7dWnPmzNGcOXP0+OOP58s+AbCmpUuXqnz58vkyW1moUCG1bt1aBw8e1I4dO\/Khd9lbunSpPD091b59+yzXlytXTnXq1NG6desc7unNjbfeektlypRRpUqV7GPlsGHDHMr0799fO3fuVEJCgrp06aLExES1atVKxpg8tVWvXj0NHDhQkvTiiy\/a26tcuXKe6gHudEFBQdqyZYu2b9+eq\/KHDh1SUlKSOnXqJEnq1KmTFi1apLS0tGtue\/HiRW3atEn333+\/w\/Ldu3fr119\/VUxMjHx8fLLctkuXLpIu3zN7pZMnT6pZs2YKDw\/XmDFjVKZMGcXFxWnGjBn2MhkZGWrZsqXefPNNtWjRQpMmTVKrVq00fvx4dejQwamtr776Sk8\/\/bQ6duyoMWPGKDU1VW3atMnX+3LDw8O1cePGHMucO3dOn3\/+uerWraty5cplWaZDhw7y8PBwOi7Xkpvz1\/T0dDVt2lQlSpTQmDFjFB4ervj4eMXHx+epLUmKjY1VkyZNJMne1pw5c\/Jcz53mn3lNAW651NRUdejQQS+\/\/LIkqW\/fvrr\/\/vv13nvvOV2Ct2fPHu3evVulS5eWdPlG+1q1amn06NEaN25crtv09vZW27ZtFRcXp+rVqztdCgjg7nP69GkdPHhQMTEx+VZntWrVJF1+UFTVqlXzrd6r7dixQxUrVszyErhMNWrU0Pr167Vnzx7de++9ua67VatWeumll+Tn55ftWOnu7q7PP\/9cbm5uki6fYL\/wwgtaunSpWrZsmeu2ypcvr7p162rixIlq0qSJ6tevn+ttgbvJ4MGD9eijj6pmzZp66KGHVLduXTVq1EgNGjSw\/zu80vz58+Xh4WEf3zp27Kjhw4drxYoVatWqVY5tHThwQOfPn3cKZJk\/ztWoUSPbbYODg+Xj46OdO3c6LD906JDGjh2r559\/XtLlsFSrVi0NHTpUnTt3lpubm+bNm6e1a9dq\/fr1qlOnjn3batWqqW\/fvtq4caPDD447d+7Ujh077LdTNGjQQDVq1ND8+fPVv3\/\/HPcxt8qXL6\/jx4\/r6NGjCggIyLLM7t27denSpRyPi4eHhypWrOh0XK4lN+evqampatq0qSZOnChJevrpp9WiRQuNHj1aAwcOlJ+fX67bq127tsLCwrRmzRrOla\/ATCzs+vbt6\/C9bt262rdvn1O5Vq1a2QOsJD300EOqVauWVqxYcdP7CODOdvr0aUlS4cKF863OzHtbz5w5k291ZuXMmTPX7Hfm+sz9zE99+vRxOHGOi4uTq6srYzNwkzRp0kRff\/21WrZsqW3btmnMmDGKjo5W6dKltWTJEqfyiYmJat68uX0cqFChgsLDw5WYmHjNtjJnMq++dzNzXMvN2HP1uOPq6qrY2Fj7d3d3d8XGxuro0aPasmWLJGnhwoWqXLmyKlWqpOPHj9s\/DRs2lCQlJSU51Nm4cWOH5wFUr15dPj4+WZ5PXq\/MY3D8+PFsy9zIcckv\/9fe\/cd6VdcPHH\/dLlx+226AfWHjgnC9KZDDkDmHJoR4KxyuYdrGTBBIyqiZSiuarGVbzLJIJgmNWYkT0GLL0jtblEydIgqsDAED2kCUDEUIuALn+4e7n\/zce8GrgPe+5PHY7uY993w+n7fn3vvmPO\/5nHPeGe0VFRXx9a9\/PRobG+NPf\/rTKXm9042IJSIiunbtGn379i1bVl1dHXv27Gmx7tlnn91iWV1dnVsxACes6e1wJzM49+3bFxH\/25nZvXt37Nq1q\/TR9PUT1atXr3cdd1t3rN6P5nNzz549o1+\/fuZmOIVGjRoVv\/3tb2PPnj3xzDPPxHe+8514880346qrrio7heEf\/\/hHPP\/88zF69OjYsmVL6WPMmDHx8MMPtzmkmp8e0DSXtGXuaT7v9O\/fP3r06FG2rK6uLiKiNG9s3rw5\/v73v0ffvn3LPprWa34Bq5qamhavfaz9yferaRs0v6\/sO53IdjkZPvKRj8TgwYPLljXftpwYbycmIqLsSnYnQ0VFRavnYR05cuSkvg7w4XLGGWdE\/\/7923yOWVs0PVdtbW1EvL3TuX379tLX586de1Luv3fuuefG888\/H4cOHTrmW4o3bNgQnTt3LgXnsXbCPui50twMJ6aqqipGjRoVo0aNirq6upg6dWqsWLGidA7kfffdFxERN910U9x0000tHv\/QQw\/F1KlTj\/n8vXv3johoEYNN56pv2LDhmI\/dvn177N27N4YOHfre\/qfi7XNiP\/nJTx7zdLEBAwaUfX6s\/cn3em7+8TRtg+O9Jbe2tjY6dep03O1y6NChePHFF+OCCy4oLfsg9187yvyflYjlPdu8eXOLZZs2bYpBgwaVPq+urm71rSPv3HGMOP5f0YDT0xVXXBGLFi2Kp556Ki666KITeq59+\/bF7373uxgwYEBpZ2\/p0qVlF1Zq\/tfy9+uKK66Ip556KlasWNHqeUvbtm2L1atXx2WXXRbdunWLiP+9Le71118vu0VH87ky4t3ny82bN8fYsWNLn+\/bty9efvnl+PznP19aVl1dHa+\/\/nrZ4xobG+Pll19+T68FHFtTFDX9XhVFEffff3+MHTs2vva1r7VY\/wc\/+EEsXbr0uBFbU1MT3bp1i61bt5Ytr6uri7q6uli5cmXMnz+\/1aOKv\/71ryPi7TnqnXbu3Bn79+8vOxq7adOmiIjSPt2QIUNi\/fr1MW7cuA4zL2zdujX69OnT4h2E79SjR48YO3Zs\/PnPf47t27fHwIEDW6yzfPnyOHToUNl2OVn7r0ePHo1\/\/vOfpaOvES237Tvn\/+O9Vlte73Tk7cS8ZytXrowdO3aUPn\/mmWfi6aefjs997nOlZUOGDImNGzfG7t27S8vWr18fTzzxRNlzNd2zq\/kvMHD6mj17dvTo0SOmT5\/e6lXPX3rppZg\/f\/67Ps+BAwfi2muvjf\/85z8xZ86c0k7A6NGj47LLLit9nKyIveGGG+LMM8+MW2+9tcVO0MGDB2Pq1KlRFEXcdtttpeVN5449\/vjjpWX79++PX\/3qVy2ev0ePHsedKxctWhRvvfVW6fOFCxfG4cOHW8zN73ytpsc1\/8t\/006tuRmObdWqVa0etWs6D\/0Tn\/hERLx9v9Jt27bF1KlT46qrrmrxcc0118SqVati586dx3ytzp07xwUXXBDPPvtsi6\/ddtttsWfPnpg5c2aL3+W1a9fGvHnzYvjw4TFp0qSyrx0+fDjuueee0ueNjY1xzz33RN++fWPkyJEREXH11VfHjh07YvHixS1e98CBA7F\/\/\/5jjvlUWbt2bZv+wPm9730viqKIKVOmtLgi\/NatW2P27NnRr1+\/svOCT+b+64IFC0r\/XRRFLFiwIDp37hzjxo2LiLcvvldZWdliTr777rtbPJc5uSVHYnnPamtr4+KLL46vfvWrcejQofjZz34WvXv3jtmzZ5fWuf766+POO++M+vr6mDZtWrz66qvxi1\/8IoYNG1Z23ke3bt1i6NChsWzZsqirq4uPfexjMXz48NLVRIHTz5AhQ+L++++Pa665Js4999z48pe\/HMOHD4\/GxsZ48sknY8WKFTFlypSyx+zYsaP0dr19+\/bFCy+8ECtWrIhdu3bFzTffXLaTcjy\/\/\/3vY\/369RHx9i0tNmzYELfffntEREycODHOO++8Yz62d+\/e8eCDD8aECRPiU5\/6VEyfPj2GDh0au3btinvvvTe2bNkS8+fPL7uS5+WXXx41NTUxbdq0uPXWW6OysjKWLFkSffv2jX\/9619lzz9y5MhYuHBh3H777VFbWxtnnnlm6eIqEW\/vgI4bNy6uvvrqePHFF+Puu++Oiy++uOzKxNOnT4+ZM2fGpEmTYvz48bF+\/fpoaGho8ba8ESNGRGVlZcybNy\/eeOON6NKlS3zmM5855pVA4XQ0a9as+O9\/\/xtf+MIX4pxzzinNUcuWLYtBgwaVjqwuXbo0KisrY8KECa0+z8SJE2POnDnxwAMPlK4U3Jorr7wy5syZE3v37i27nc7kyZNjzZo1MX\/+\/HjhhRdi8uTJUV1dHc8991wsWbKkNDc1v2Jy\/\/79Y968ebFt27aoq6uLZcuWxbp162LRokWlda+99tpYvnx5zJw5M1atWhWjR4+OI0eOxMaNG2P58uXR0NBQ9nbcU+3VV1+NDRs2xI033viu637605+OH\/\/4x\/Gtb30rzjvvvJgyZUr069cvNm7cGIsXL46jR4\/GH\/\/4x7KLZZ2s\/deuXbvGo48+Gtddd11ceOGF8cgjj8Qf\/vCH+O53v1s6gvzRj340vvjFL8Zdd90VFRUVMWTIkHj44YdbnGccEaU\/KnzjG9+I+vr6qKysjC996UsntC3Ta6f709KOmt9kuummzM01v\/F0082X77jjjuInP\/lJMWDAgKJLly7FJZdcUqxfv77F4++7775i8ODBRVVVVTFixIiioaGh7GbRTZ588sli5MiRRVVVVdnNooHT26ZNm4oZM2YUgwYNKqqqqopevXoVo0ePLu66667i4MGDpfUGDhxYuvl7RUVFccYZZxTDhg0rZsyYUTz99NPv6TWPdVP5eMeN59\/N1q1bixkzZhQ1NTVF586diz59+hQTJ04sVq9e3er6a9euLS688MKiqqqqqKmpKe68887SPL1169bSert27SomTJhQ9OrVq4iI4tJLLy2K4n9z+l\/\/+tfiK1\/5SlFdXV307NmzmDx5cvHaa6+VvdaRI0eKb3\/720WfPn2K7t27F\/X19cWWLVuKgQMHFtddd13ZuosXLy4GDx5cVFZWFhFRrFq1qo1bEU4PjzzySHH99dcX55xzTtGzZ8+iqqqqqK2tLWbNmlW88sorRVEURWNjY9G7d+\/ikksuOe5znXXWWcX5559\/3HVeeeWVolOnTsVvfvObVr++cuXKYvz48UV1dXXRpUuXora2trj55puL3bt3t1j30ksvLYYNG1Y8++yzxUUXXVR07dq1GDhwYLFgwYIW6zY2Nhbz5s0rhg0bVnTp0qWorq4uRo4cWXz\/+98v3njjjdJ6EVHceOONLR7ffH5ZsmRJERHFc889V1rWfJ+ztccVRVEsXLiw6N69e7F3795Wt0FrHn\/88eLKK68s+vTpU3Tu3LmoqakpZsyYUWzbtq3V9U90\/7Vpv\/qll14qLr\/88qJ79+7Fxz\/+8WLu3LnFkSNHyp5j9+7dxaRJk4ru3bsX1dXVxQ033FD87W9\/a\/FvzuHDh4tZs2YVffv2LSoqKlpsq9NRRVGcxDOt+VDbtm1bnHXWWXHHHXfELbfc0t7DASAi7r333pg6dWqsWbPmAz0iAnzwpk2bFps2bYrVq1ef0POMGTMm\/v3vf5\/Ui+i11c9\/\/vP45je\/GVu2bCm7HU9zAwYMiPr6+vjlL39ZWnb++efHmDFj4qc\/\/ekHMdT3ZcqUKfHggw+etCvf0zpvJwYAgATmzp0bdXV18cQTT8To0aPbezjvy5o1a6JHjx6tXmypyVtvvRWvvfZa2akOjz76aGzevDkaGho+iGHSwYlYAABIoKamJg4ePNjew3hfHnroofjLX\/4SS5cujenTp0enTq1nSENDQzzwwANx4MCB0kWQIiI++9nPOrpJiYgFAABOqVtuuSXefPPNmDZt2nHfDvyjH\/0otmzZEj\/84Q9j\/PjxH+AIycQ5sQAAAKThPrEAAACkIWIBAABIQ8QCAACQhogFAAAgjTZfnfjorrNP5TjSqe8\/or2HEBERDTvXtfcQOoyO8j2h3GNHV7T3EE458yPwfnzk\/za39xBOuY4yP9pHKNcR9h87yvekI2wLWnq3+dGRWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpdGrrivX9R5zCYbRdw8517T2EiOg44+gIOsrPRkfRUX42fF8AAPgwciQWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDQ6tXXFhp3rTuEw2q6+\/4j2HkKH0hG+Lx1hDBEd52ejo4wDAAA+jByJBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACCNTm1dsb7\/iFM4jLZr2LmuvYcQER1ne3QEHWVb+Nko11G2BwAAnEyOxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIo1N7D+C9qu8\/or2HEBERDTvXtfcQOgzbgtNdR5mXgFweO9reIwDIyZFYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANLo1NYVG3auO4XDaLv6\/iPaewgR0XHGAcfSUX5GHzva3iMAAKAtsuw\/OhILAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBqd2nsA5Newc117D6FDqe8\/or2HEBG+Lx8k2xoA+DDIsk\/jSCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaXRq7wFk1bBzXXsPocOo7z+ivYcQER3ne9JRxsHpx+8iQMdmfqSj6yj7Eo8dPf7XHYkFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAIA0RCwAAQBoiFgAAgDRELAAAAGmIWAAAANIQsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACkIWIBAABIQ8QCAACQhogFAAAgDRELAABAGiIWAACANEQsAAAAaYhYAAAA0hCxAAAApCFiAQAASEPEAgAAkIaIBQAAII2KoiiK9h4EAAAAtIUjsQAAAKQhYgEAAEhDxAIAAJCGiAUAACANEQsAAEAaIhYAAIA0RCwAAABpiFgAAADSELEAAACk8f+cOsNbyoduXQAAAABJRU5ErkJggg==\" \/><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>10\u756a\u76ee\u306eBar\u3068Stripe\u306b\u3064\u3044\u3066\u753b\u50cf\u518d\u69cb\u6210\u3092\u884c\u3046\u3068\u3001\u30b1\u30fc\u30b9A\u3068\u30b1\u30fc\u30b9B\u306e\u5834\u5408\u306f\u3046\u307e\u304f\u518d\u69cb\u6210\u3067\u304d\u3066\u3044\u307e\u3059\u304c\u3001\u30b1\u30fc\u30b9C\u306e\u5834\u5408\u306f\u3069\u3061\u3089\u3082\u6570\u30d3\u30c3\u30c8\u9593\u9055\u3063\u3066\u3044\u308b\u69d8\u5b50\u304c\u898b\u3089\u308c\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h4><span class=\"ez-toc-section\" id=\"%E7%94%BB%E5%83%8F%E5%86%8D%E6%A7%8B%E6%88%90%E3%81%AE%E3%82%A8%E3%83%A9%E3%83%BC%E5%88%86%E5%B8%83\"><\/span>\u753b\u50cf\u518d\u69cb\u6210\u306e\u30a8\u30e9\u30fc\u5206\u5e03<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u7d9a\u3044\u3066\u3001\u5177\u4f53\u7684\u306b\u3069\u306e\u304f\u3089\u3044\u30d3\u30c3\u30c8\u3092\u9593\u9055\u3063\u3066\u3044\u308b\u304b\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306b\u3001\u30b1\u30fc\u30b9B\u306b\u3064\u3044\u3066\u518d\u69cb\u6210\u3057\u305f\u6642\u306b\u5143\u306e\u753b\u50cf\u3068\u306e\u8aa4\u308a\u30d3\u30c3\u30c8\u6570\u3092\u8a08\u7b97\u3057\u3001\u8a13\u7df4\u30c7\u30fc\u30bf\u3068\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u306e\u5834\u5408\u3067CD\u5b66\u7fd2RBM\u3068SA\u5b66\u7fd2RBM\u306e\u6bd4\u8f03\u3092\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"c1\"># \u753b\u50cf\u306e\u53f3\u4e0b4\u00d74(16\u30d3\u30c3\u30c8)\u306b\u5bfe\u5fdc\u3059\u308b\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u3092\u914d\u5217\u306b\u52a0\u3048\u308b<\/span>\r\n<span class=\"n\">mask_indices<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n<span class=\"k\">for<\/span> <span class=\"n\">r<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"mi\">8<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">c<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"mi\">8<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">mask_indices<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">r<\/span> <span class=\"o\">*<\/span> <span class=\"mi\">8<\/span> <span class=\"o\">+<\/span> <span class=\"n\">c<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"n\">mask_indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">array<\/span><span class=\"p\">(<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">mask_indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">[<\/span><span class=\"n\">mask_indices<\/span> <span class=\"o\">&lt;<\/span> <span class=\"mi\">62<\/span><span class=\"p\">]<\/span>\r\n\r\n<span class=\"c1\"># \u8aa4\u308a\u30d3\u30c3\u30c8\u6570\u306e\u8a08\u7b97<\/span>\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"Calculating reconstruction errors for CD and SA models...\"<\/span><span class=\"p\">)<\/span>\r\n<span class=\"c1\"># \u30af\u30e9\u30b9\u30e1\u30bd\u30c3\u30c9\u3068\u3057\u3066\u547c\u3073\u51fa\u3057<\/span>\r\n<span class=\"n\">cd_train_errors<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">get_incorrect_bits<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">cd_test_errors<\/span>  <span class=\"o\">=<\/span> <span class=\"n\">rbm_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">get_incorrect_bits<\/span><span class=\"p\">(<\/span><span class=\"n\">test_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">sa_train_errors<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">get_incorrect_bits<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">sa_test_errors<\/span>  <span class=\"o\">=<\/span> <span class=\"n\">rbm_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">get_incorrect_bits<\/span><span class=\"p\">(<\/span><span class=\"n\">test_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u63cf\u5199<\/span>\r\n<span class=\"n\">fig<\/span><span class=\"p\">,<\/span> <span class=\"n\">axes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">subplots<\/span><span class=\"p\">(<\/span><span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">figsize<\/span><span class=\"o\">=<\/span><span class=\"p\">(<\/span><span class=\"mi\">12<\/span><span class=\"p\">,<\/span> <span class=\"mi\">10<\/span><span class=\"p\">))<\/span>\r\n\r\n<span class=\"n\">max_bits<\/span> <span class=\"o\">=<\/span> <span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">mask_indices<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">bins<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">arange<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">max_bits<\/span> <span class=\"o\">+<\/span> <span class=\"mi\">2<\/span><span class=\"p\">)<\/span> <span class=\"o\">-<\/span> <span class=\"mf\">0.5<\/span>\r\n\r\n<span class=\"k\">def<\/span><span class=\"w\"> <\/span><span class=\"nf\">plot_hist<\/span><span class=\"p\">(<\/span><span class=\"n\">ax<\/span><span class=\"p\">,<\/span> <span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"n\">title<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">ax<\/span><span class=\"o\">.<\/span><span class=\"n\">hist<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"n\">bins<\/span><span class=\"o\">=<\/span><span class=\"n\">bins<\/span><span class=\"p\">,<\/span> <span class=\"n\">rwidth<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.8<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"o\">=<\/span><span class=\"n\">color<\/span><span class=\"p\">,<\/span> <span class=\"n\">edgecolor<\/span><span class=\"o\">=<\/span><span class=\"s1\">'black'<\/span><span class=\"p\">,<\/span> <span class=\"n\">alpha<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.7<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">ax<\/span><span class=\"o\">.<\/span><span class=\"n\">set_title<\/span><span class=\"p\">(<\/span><span class=\"n\">title<\/span><span class=\"p\">,<\/span> <span class=\"n\">fontsize<\/span><span class=\"o\">=<\/span><span class=\"mi\">14<\/span><span class=\"p\">,<\/span> <span class=\"n\">fontweight<\/span><span class=\"o\">=<\/span><span class=\"s1\">'bold'<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">ax<\/span><span class=\"o\">.<\/span><span class=\"n\">set_xlabel<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"No. of incorrectly predicted bits\"<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">ax<\/span><span class=\"o\">.<\/span><span class=\"n\">set_ylabel<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"No. of instances\"<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">ax<\/span><span class=\"o\">.<\/span><span class=\"n\">set_xticks<\/span><span class=\"p\">(<\/span><span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"n\">max_bits<\/span> <span class=\"o\">+<\/span> <span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">))<\/span>\r\n    <span class=\"n\">ax<\/span><span class=\"o\">.<\/span><span class=\"n\">set_ylim<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">150<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"n\">ax<\/span><span class=\"o\">.<\/span><span class=\"n\">grid<\/span><span class=\"p\">(<\/span><span class=\"n\">axis<\/span><span class=\"o\">=<\/span><span class=\"s1\">'y'<\/span><span class=\"p\">,<\/span> <span class=\"n\">linestyle<\/span><span class=\"o\">=<\/span><span class=\"s1\">'--'<\/span><span class=\"p\">,<\/span> <span class=\"n\">alpha<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.5<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># CD\u5b66\u7fd2RBM\u306e\u8aa4\u308a\u30d3\u30c3\u30c8\u6570(\u8a13\u7df4\u30c7\u30fc\u30bf)<\/span>\r\n<span class=\"n\">plot_hist<\/span><span class=\"p\">(<\/span><span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span><span class=\"p\">],<\/span> <span class=\"n\">cd_train_errors<\/span><span class=\"p\">,<\/span> <span class=\"s2\">\"D: CD; Training Data\"<\/span><span class=\"p\">,<\/span> <span class=\"s1\">'tab:blue'<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># CD\u5b66\u7fd2RBM\u306e\u8aa4\u308a\u30d3\u30c3\u30c8\u6570(\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf)<\/span>\r\n<span class=\"n\">plot_hist<\/span><span class=\"p\">(<\/span><span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">],<\/span> <span class=\"n\">cd_test_errors<\/span><span class=\"p\">,<\/span> <span class=\"s2\">\"E: CD; Test Data\"<\/span><span class=\"p\">,<\/span> <span class=\"s1\">'tab:blue'<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># SA\u5b66\u7fd2RBM\u306e\u8aa4\u308a\u30d3\u30c3\u30c8\u6570(\u8a13\u7df4\u30c7\u30fc\u30bf)<\/span>\r\n<span class=\"n\">plot_hist<\/span><span class=\"p\">(<\/span><span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span><span class=\"p\">],<\/span> <span class=\"n\">sa_train_errors<\/span><span class=\"p\">,<\/span> <span class=\"s2\">\"F: SA; Training Data\"<\/span><span class=\"p\">,<\/span> <span class=\"s1\">'tab:orange'<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># SA\u5b66\u7fd2RBM\u306e\u8aa4\u308a\u30d3\u30c3\u30c8\u6570(\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf)<\/span>\r\n<span class=\"n\">plot_hist<\/span><span class=\"p\">(<\/span><span class=\"n\">axes<\/span><span class=\"p\">[<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">],<\/span> <span class=\"n\">sa_test_errors<\/span><span class=\"p\">,<\/span> <span class=\"s2\">\"G: SA; Test Data\"<\/span><span class=\"p\">,<\/span> <span class=\"s1\">'tab:orange'<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">tight_layout<\/span><span class=\"p\">()<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">show<\/span><span class=\"p\">()<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_subarea output_stream output_stdout output_text\">\n<pre>Calculating reconstruction errors for CD and SA models...\r\n<\/pre>\n<\/div>\n<\/div>\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_png output_subarea\"><img decoding=\"async\" alt=\"No description has been provided for this image\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAABKUAAAPeCAYAAADd\/6nHAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAA6cNJREFUeJzs3Xd8VHX2\/\/H3TDophNBCDGBogjRRihQFBSmiIrIKLiIi4leEpaiIuiKgrii6iqLCj1UBd23oAiuoIEsVKVLFgoAh9N4SEkhIZj6\/P9hcM2kkMLmTDK\/n45HHI3PmzueeMzNhDmfu3HEYY4wAAAAAAAAAGzl9nQAAAAAAAAAuPwylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHYMpQAglw4dOsjhcMjhcOiBBx645PWWLVtmredwOLRr165LXhMAAAAAyjqGUkAJyj2McDgcCg4OVvny5VWrVi116tRJ48eP1969e0s0j++\/\/14PP\/ywGjVqpOjoaAUFBalSpUq64YYbNHbsWCUmJvo05\/z2eaGfK6+80mv7x3m57+PAwEBFREQoPj5ebdq00bBhw7R+\/Xqv7nPcuHE8pgAAWxW17\/DGG1O5bdmyRcOGDVOzZs0UExOjoKAgVahQQS1bttSoUaO0ZcsWa9tdu3blySkoKEiRkZGqWbOm2rdvr9GjR+u3337zWn757bMoPyXtgQcesPbVoUOHYt8+5xuODodDAQEBCgsLU9WqVdWsWTP169dPX375pVwul9dy5k1JoGgCfZ0AcLnJzMxUZmamUlJSlJSUpMWLF+uFF17QmDFjNGbMGDmd3psVnzx5Ug8++KDmzp2b57rjx49r5cqVWrlypZYvX65ly5aVipxLg8GDB+u2226TJDVq1OiS16tdu7ZeffVV63JMTMwlr2kHl8ultLQ0paWlaf\/+\/Vq9erUmT56su+66S++9954qVKjg6xQBACgT0tPTNXz4cE2bNi3PdadOndK6deu0bt06ff7554UOL7KyspSamqrU1FTt2bNHK1as0MSJEzV48GC9\/vrrCg0NLcEq\/Ifb7VZ6errS09N15MgRbd68Wf\/617\/UqFEjffrpp2rYsKGvUwQuGwylABv17t1bzZs3V3JysjZu3KiFCxfK5XLJ5XJp3LhxOnTokKZMmeKVfaWlpalz584eR7bExsbqzjvvVI0aNXT69Glt3LhRixcv9nnOuYc2kvTtt99q0aJF1uVnnnnGYwhSvnz5Qtc8ffq0IiMjLyqf3r17X9TtClK9enU98cQTXl2zpDVv3ly9e\/fWmTNntGPHDs2bN0\/JycmSpNmzZ2vXrl367rvvVK5cOR9nCgDApcnudXLzxhtT0vk3ee655x7NmzfPipUvX1533XWX6tSpo\/T0dG3ZskXffvttoevccsst6ty5s1JTU\/Xzzz\/rq6++Unp6uiRpypQp2rNnj\/7zn\/8oICDgonONiYnJ05OtX79en332mXX5kUceUe3atS96H75WoUIFPfPMM8rMzNTevXv1zTffWIPAn3\/+We3atdPq1atVv3593yYKXC4MgBKzdOlSI8n6mT59usf1v\/76q0lISPDY5ptvvvHYpn379tZ17du3L\/K+n3rqKY91e\/ToYdLS0vJst3\/\/fjN16tRSkXNOY8eO9dhHUlJSgdfXrFnTHDt2zDz66KPmiiuuME6n07zxxhvGGGNmz55t7rvvPtO4cWNTpUoVExQUZMLDw02DBg3MkCFD8qybO\/\/+\/ftb8aSkJI+cli5daj755BPTsmVLExYWZqKjo82f\/vQns2fPHo\/1ct+nOffZv39\/j\/vqwIEDZtCgQSY2NtYEBweb+vXrm2nTpuV7H23ZssXcdtttJjIy0kRGRpquXbuaTZs25blviipnjjnrNsaYkydPmq5du3psM3r0aI9t3n\/\/fXP33Xeb+vXrm4oVK5rAwEATGRlpmjZtap588klz9OjRAu+T\/H6yn3s7d+40w4cPN+3atTPx8fGmXLlyJjg42MTFxZnbbrvNfPnll0WuEQCAC\/U6Bcn5ml2c19epU6d67K9169Yer4nZTpw4YfUvxuTtO8aOHeux\/b59+8x1113nsc2UKVO8knNO06dPz9P\/5JacnGxeeukl07JlSxMVFWWCgoJM9erVTf\/+\/c3PP\/+cZ\/vMzEzzxhtvmOuvv96UL1\/eBAQEmJiYGHP11Vebfv36mU8++STffef3k18+ueXs7XLfD1lZWeavf\/2rx5qtWrXy2Gbp0qXmwQcfNM2aNbN6tLCwMFO7dm3zwAMPmC1btnhsf6Gcs\/uszMxM8+yzz5pu3bqZWrVqmfLly5vAwEATExNj2rVrZ9566y1z7ty5C9YHlGUMpYASVJSm54cffvDYpnPnzh7XX8yA59y5cyYyMtK6XWxsrElNTS3VOedWnKFUpUqVTP369T22z27qevXqVWhTEBUVlaeRKOpQql27dvmuWbduXXP27NkC79OChlK1atUy1apVy3fN999\/3yPHdevWmYiIiDzbhYaGmltuucXrQyljjDl9+rSpWrWqtU1ERITJyMiwrs\/dGOf+ueKKK8z+\/fvzvU8KG0rNmzfvgtuOHz++yHUCAC5vdg+lcvYooaGh1mvhhVxoKGWMMXv37jWhoaHWNvXq1fNKzjldaCi1fft2c+WVVxb4Gh0SEmJmzZpVYF75\/WQPhewYSmXr3r27x7qrVq2yrnv88ccLzSE4ONgsWrTI2v5COWf3WadPn77gtp06dTJZWVkXfqCAMoqP7wE+1qJFCzVt2lQ\/\/vijJGnFihVyuVyXdOj1unXrdPr0aety7969FR4efsm5ZiuJnC\/FsWPHdOzYMXXq1Elt27bV0aNHVbVqVUlSdHS0OnfurAYNGqhChQoKDg7W4cOHNWfOHO3Zs0cpKSkaPXq0vv7662Lvd+XKlWrRooW6dOmipUuX6vvvv5ck7dixQ3PnzlWfPn2Ktd7OnTsVGhqqwYMHKywsTFOmTNHZs2clSRMnTtSDDz4oSTLG6MEHH1Rqaqp123vvvVe1atXSrFmzPD726E0RERHq06eP3nzzTUlSamqq1q9frzZt2kiSqlSpottvv121a9dWTEyMAgICtH\/\/fn322Wc6fvy49u\/frxdffFHvvvuu9ZHNnB\/TzD6cPluLFi0kSYGBgbrmmmvUvHlzVa5cWVFRUUpLS9P333+vpUuXSpJeeOEFDRw4UFdccUWJ1A4A8F8LFizQsWPH8sR79+6t6tWrX9LaBw4c8DgReZcuXRQXF3dJa+YUHx+vLl266D\/\/+Y8kafv27Tpw4IBX91EYl8ulnj17Wh9\/q1y5sv785z8rJiZGCxcu1KpVq5SRkaH7779f1113nWrVqqXU1FT961\/\/stbo1auXrr32WiUnJ2v37t1avny5dV2LFi306quv6rPPPrNOSVGrVi0NHjzY2sZbHyV86KGH9NVXX1mXly5dqtatW0uSwsPD1b59ezVu3FgxMTEKCwvT8ePH9dVXX2nr1q06d+6chg0bpl9\/\/VWS9OqrryoxMVFTp0611st5Korsj4Y6HA7VqlVL119\/va644gpVqFBBmZmZ+u233\/T5558rKytL\/\/3vf\/Xvf\/9b99xzj1fqBEobhlJAKXDVVVdZA5709HSdOHFClStXvuj19u\/f73G5JD4T7+2cL9WIESP0xhtv5Im\/9957yszM1Jo1a7Rjxw6lpKQoPj5eHTt21PTp0yVJS5YsUWZmpoKCgoq1z5YtW2rlypUKCgpSZmam4uPjdeTIEUnnB4PFHUpJ0qeffqoePXpIkmrUqKERI0ZIkrZt22adJ2vt2rX66aefrNuMHj1aL7\/8siTp8ccfV+3atXXy5Mli77sorrrqKo\/LOZ9rX3\/9tc6cOaPVq1dr586dSk1NVUJCgtq1a2c1ywsXLpT0x3m2UlNTraFUVFRUvufe6tq1q7p27art27dr06ZNOnr0qIKCgnTrrbdq7dq1OnPmjLKysrRkyRL169evROoGAPivzz77zOOcSdmaN29+yUMpu3qy3Pu0ayj11Vdf6ZdffpEkBQQE6Pvvv1fdunUlSX\/961\/VrFkz\/fTTT0pPT9fbb7+t119\/XZmZmda33EVFRenjjz9WcHCwtaYxxhpyNWzYUA0bNtTPP\/9sDaVK6lydhfU448ePl9vt1vr167V161adOnVKVatWVbdu3bR161ZJ0tatW7V3714rv2XLlnkMpQYNGpTnm4bDw8OVmJioI0eOaM2aNdq\/f7\/OnDmja6+9Vj\/99JN+\/vlnSef7J4ZS8FcMpYBSwBhT4HWFfSueL5W2nJ999tl84x999JFGjBiR7zug2TIyMnTs2DFVq1atWPt86KGHrEFWUFCQEhISrKHUxQyF4uLirIGUlLc5OnnypCIjIz1OXi9J999\/v\/V7hQoV1KNHD82YMaPY+y+Kwh73119\/XWPHjvU4giu3ffv2FXufu3btUt++fbVq1apCt7uYtQEAKKoZM2aU2OvrpSjstbmkc84+Slw6f9RUvXr1Ctw2+3W8QoUKatiwoX755RelpKQoISFBLVq0UN26ddW4cWN17NhRCQkJJZZzQQq7HxctWqSHHnpIe\/bsKXSNffv2FWuQefbsWT366KP68MMP5Xa7C10X8FcMpYBSYPv27dbvoaGhqlix4iWtl\/sjTDkPG\/cWb+d8KSpVqpTv\/jdu3Kj777+\/0Bf5bBkZGcXeb+53u0JCQqzfi7LP4qyXc81Tp055xGNjYwu97E05H3fpj+fa3Llz9fjjj1\/w9ufOnSv2Pu+8807rqLzCXMxjCADA9OnT9cADD5TI2nb3ZPntsySdOHGiyNsePXrU+v3jjz\/Wvffeq19\/\/VUHDhywjqiWJKfTqeHDh+v111\/3aq4XUtD9eODAAd155506c+bMBdcobi\/y9NNPF2loSI8Df+b0dQLA5W79+vUe\/+Fu3769nM5L+9Ns0aKFIiMjrcuzZs0q0gtpUZVEzpeioPNlff7559Ygx+Fw6JNPPlFqaqqMMR7nDLhYuT\/u53A4bFkvOjra43L20VnZDh06dEl5FCQtLc3j4w2RkZHWV2jnjEdEROjbb7\/V2bNnZYzRO++8c9H73LZtm8dz7c9\/\/rP27dsnt9stY4xPPzIKAMCFxMXFeXxkb+HChTp48KDX1t+\/f7\/10Xjp\/FHWdn10T5JiYmKs30NDQ\/Xqq68W+PPUU09Z2zZp0kS\/\/PKLtmzZohkzZuivf\/2runXrJun8m3BvvPGGdd5Iu7z\/\/vsel2+++WZJ0rx58zz66L\/\/\/e86deqUjDHWRxcvVs7+qXHjxvr555+VmZkpY4zuvvvuS1obKCsYSgE+tG3btjznHXrsscc8Lnfo0EEOh0MOh0MdOnQo0rpBQUF69NFHrcsHDx5Uv379rJNm53TgwAFNmzbN5zmXhOPHj1u\/ly9fXvfcc481wJo1a5av0rpk2YOgbJ988on1+8mTJz3ebfSWlJQU9e7d22PgNXToUOscEDnv61q1aumWW25RaGio3G63vvjiiwLXzTmIy29wmnNdSfrTn\/6kK664Qg6HQ8uWLfN41xUAgJL0wAMPWP1N7qObCzN8+HDr9\/T0dN199935HmF08uRJTZo0qcjrHjx4UHfddZfS09OtWO6e7GJzLqrsLzuRztfWsGFDPfHEE3l+brjhBusLTCRp8+bNks4PYvr3768XX3xRX3\/9tZo0aWJts3HjRuv3C\/ULl8Ltdmvs2LGaP3++FWvdurWuv\/56SXl7kQEDBqh8+fKSCu8nc7\/ZeKE+56abblLDhg0VGBioo0ePltpTeADexsf3ABtlf7tLSkqKNm3apAULFigrK8u6fsiQIercubNX9vXss89q0aJF1gv67NmzVbt2bfXs2VPx8fE6ffq0Nm7cqMWLF6tt27Z6+OGHfZ6zt+U8J9OpU6fUvXt3tWnTRitXrtS3337rw8wuzfXXX6\/GjRtbJzt\/4YUXlJSUpBo1amjWrFleOcn5L7\/8otdee03p6enavn275s2b5\/GxwRYtWmjMmDHW5auuuso6YfmWLVt07733qkGDBvrmm2+0Zs2aAveT8yMGR48e1YABA3T11VfL4XBoyJAhqlOnjpxOp3XE2\/Dhw7V582YdP37cOlE9AACXoqBv3ytfvrwGDRp0yesPGjRIX375pb755htJ58\/DVLt2bd11112qXbu20tPTtWXLFn377beqUqWK9SUnua1atUqvvfaa0tLS9Msvv2j+\/Pkebzjefvvteuihhy453+Lo3r27GjRoYJ3s+84779Rdd92lq6++Wm63W4mJiVqxYoV2796t6dOn65prrpF0vpeJi4vTDTfcoLi4OEVFRenHH3\/Uli1brLVzHhmes1\/YsGGDhg8frurVqys4OFjDhg0rVs4pKSl67bXXlJmZqf379+ubb77Rzp07resrVKjg8ZG63Of47N69u7p166YtW7YU+sZb7o9RDhkyRF26dFFgYKDuuOMO1atXT1dddZV1MvN\/\/OMfcjqdKleunP75z3\/yxhsuHwZAiVm6dKmRdMGfwMBA88ILLxiXy5Vnjfbt21vbtW\/fvlj7P3bsmLntttsuuP+c6\/o652xjx4712F9SUlKB19esWTPfNY4fP27i4uLyzb9\/\/\/4Frp8z\/\/79+1vxpKQkj9ssXbq0wLpz3i73fZpzXznzyH1fFXa7devWmYiIiDx1hYSEmJtvvtm6nJCQcOE7+3+K8rhLMnfffbc5deqUx2137NhhIiMj832e9O3b1yOW08GDB025cuXy3c\/Ro0eNMcY88sgj+V7fsWNHc8UVV1iXx44dW+RaAQCXr6L2Orn7i5yv2QX1HgVJS0szAwcOLNY+c\/cdBf04HA4zdOhQk56enme\/l5JztunTpxfa\/2zbts1ceeWVF8xz+vTp1m1CQkIK3TYhIcGj19i0aZNxOp15tgsPDy9SDTl7tMJ+mjZtarZu3epx23PnzpnGjRsXqZ\/Mfd80a9Ys39t9\/vnnxhhjPvnkk3yvr1atmrnlllsK7BEBf8LH9wCbBQQEKDIyUgkJCerYsaPGjx+vXbt26dlnn\/X6eZkqVqyoefPmafny5Ro4cKAaNGigqKgoBQQEKCYmRu3atdPEiRP14YcfejXnnOc4ynlYt91iYmK0cuVK3XXXXYqKilJYWJhatGih2bNnl9gJTe3SvHlzrVq1St27d1dERIQiIiLUsWNHrVixwvoqZinv+aeKw+l0KiwsTHFxcWrdurX+8pe\/aMOGDZo1a5Z12Hq2OnXqaMWKFercubPKlSuniIgItW\/fXosXL1anTp0K3EdsbKzmzZuntm3bFnhusMmTJ+v5559XzZo1FRQUpBo1amjUqFGaN2+eAgM54BcAUPqVK1dO7733njZt2qShQ4eqadOmio6OVkBAgMqXL68WLVpo7NixWrBgQaHrOJ1OhYeHq3r16rrxxhs1evRobdu2TZMnT87zBSmSPT1ZvXr1tGXLFk2cOFFt2rRRhQoVrN6xSZMmeuihhzRnzhz9+c9\/tm4zZcoUDRgwQE2aNFHlypUVGBioiIgINWnSRE8++aTWrl3r0Wtcc801+uSTT3TttdcqNDT0knN2OBwKCQlR5cqV1bRpU\/Xr109ffvmlNm7c6HEOMOn8x\/CWLFmiBx54QBUrVlRISIgaNWqkadOmady4cYXuZ\/bs2erZs6diYmLyPVdonz59NGvWLDVt2lRBQUGqWLGievfurTVr1th6bjDAlxzGFPLdlwBQTEeOHFHVqlUlSQkJCfrll18UFhbm46z8z7lz5xQYGJhnKJiamqpGjRpp9+7dks5\/ZKA45wwDAAD+weVyqUKFCjp9+rSio6O1devWEv2GXgC4GLzFDMCrli9fbv3+7rvvMpAqIb\/++qvuuOMO9e3bV1dffbUqVKigXbt2aerUqdZAyul0asiQIT7OFAAA+MLGjRt1+vRpSdKECRMYSAEolRhKAfCq7KFU79691bVrVx9n49\/27t2rl19+Od\/rgoODNWXKFDVt2tTmrAAAQGmQ3ZO1bt1a\/\/d\/\/+fjbAAgf3x8DwDKoOPHj+tvf\/ubli1bpj179ig5OVmhoaFKSEhQhw4d9Oijj+Y5JwIAAAAAlCYMpQAAAAAAAGA7vn0PAAAAAAAAtmMoBQAAAAAAANtxonNJbrdbBw4cUGRkpBwOh6\/TAQAApYgxRqdPn1ZcXJycTt7Py0b\/BAAAClLU\/omhlKQDBw6oevXqvk4DAACUYnv37lV8fLyv0yg16J8AAMCFXKh\/YiglKTIyUtL5OysqKsqra+\/cuVMPDhmpGl0eUmTlOK+uffroAe1Z+J4+eOcN1apVy6trAwCA81JSUlS9enWrX8B5Jdk\/AQCAsq2o\/RNDKck65DwqKsrrTVVkZKQCAgMVFFpOwWERXl07KLScAgIDFRkZSTMIAEAJ4yNqnkqyfwIAAP7hQv0TJ0YAAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALCdT4dSK1as0O233664uDg5HA7NnTu3wG0feeQRORwOTZo0ySN+4sQJ9e3bV1FRUYqOjtbAgQOVmppasokDAAD4ED0UAADwBz4dSqWlpalp06Z65513Ct1uzpw5WrNmjeLi4vJc17dvX\/3yyy9atGiR5s+frxUrVujhhx8uqZQBAAB8jh4KAAD4g0Bf7rxbt27q1q1bodvs379ff\/nLX7Rw4UJ1797d47qtW7dqwYIFWrdunZo3by5Jmjx5sm699Va99tpr+TZgAAAAZR09FAAA8Ael+pxSbrdb\/fr106hRo9SwYcM8169evVrR0dFWMyVJnTp1ktPp1Nq1a+1MFQAAoNSghwIAAGWBT4+UupBXXnlFgYGBGjZsWL7XHzp0SFWqVPGIBQYGKiYmRocOHSpw3YyMDGVkZFiXU1JSJEkul0sul0uS5HA45HQ65Xa7ZYyxti0o7nQ65XA48sSzf3c6JKf+iLuzb5crt4LjDknGI579uzHGyvtici9uTdnxnPvMjkvnG+GixAMCAmSM8Yhn51JQnJqoiZqoiZqoye6acq9XFpRED2Vn\/8Tzk5qoiZqoiZqoqWzXVNT+qdQOpTZs2KA333xTGzdulMPh8OraEyZM0Pjx4\/PEExMTFRERIUkqX768qlWrpsOHDys5OdnaplKlSqpUqZL279+vtLQ0Kx4bG6vo6Gjt2rVL586ds+LZD0iDClK50NNWPCkjXFnGqbo5YpK0Iz1SgQ63EkL+WNslh35Pj1S406X44DNWPDla2ikpPT1dO3bssOLh4eGqXr26Tpw4oWPHjllxb9UUHx+viIgIJSYmejwRExISFBgY6JGLJNWtW1dZWVlKSkqyYk6nU\/Xq1VNaWpr27dtnxYODg1WrVi0lJyd7NMXURE3URE3URE2+qqmsnfy7pHooO\/snnp\/URE3URE3URE1lu6ai9k8Ok3NE5kMOh0Nz5szRnXfeKUmaNGmSHnvsMWsKJ52ftDmdTlWvXl27du3SBx98oMcff1wnT560tsnKylJoaKg+\/\/xz9ezZM9995fdOX\/aDHBUVZeXjjaljUlKS7h04WLVue1RRla+w4t44UirlyH7t\/OpdffL+FCUkJFwwx9I+Sc2Zi79Mh6mJmqiJmqip7NeUkpKimJgYJScnW31CaWJXD2Vn\/8Tzk5qoiZqoiZqoqWzXVNT+qdQeKdWvXz916tTJI9alSxf169dPAwYMkCS1bt1ap06d0oYNG3TddddJkpYsWSK3261WrVoVuHZISIhCQkLyxAMCAhQQEOARy9nQXUw8+x1Kt8keLHly54kUFnd4xLN\/dzgcefIuTo4XG89vn8WNF5Q7NVFTYXFqoiZqoqbC4t6uqaDblVYl1UPZ2T\/lXPtS4\/7+\/CxKnJqoqaAcixunJmq6mDg1XZ41FbV\/8ulQKjU1Vb\/\/\/rt1OSkpSZs3b1ZMTIxq1KihihUremwfFBSk2NhYXXXVVZKkBg0aqGvXrho0aJCmTp2qzMxMDR06VH369OFbYwAAgN+ihwIAAP4g\/xGZTdavX69mzZqpWbNmkqTHHntMzZo103PPPVfkNT766CPVr19fHTt21K233qp27dpp2rRpJZUyAACAz9FDAQAAf+DTI6U6dOjg8VnGC9m1a1eeWExMjD7++GMvZgUAAFC60UMBAAB\/4NMjpQAAAAAAAHB5YigFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHY+HUqtWLFCt99+u+Li4uRwODR37lzruszMTI0ePVqNGzdWeHi44uLidP\/99+vAgQMea5w4cUJ9+\/ZVVFSUoqOjNXDgQKWmptpcCQAAgH3ooQAAgD\/w6VAqLS1NTZs21TvvvJPnujNnzmjjxo0aM2aMNm7cqNmzZ2vbtm264447PLbr27evfvnlFy1atEjz58\/XihUr9PDDD9tVAgAAgO3ooQAAgD8I9OXOu3Xrpm7duuV7Xfny5bVo0SKP2Ntvv62WLVtqz549qlGjhrZu3aoFCxZo3bp1at68uSRp8uTJuvXWW\/Xaa68pLi6uxGsAAACwGz0UAADwB2XqnFLJyclyOByKjo6WJK1evVrR0dFWMyVJnTp1ktPp1Nq1a32UJQAAQOlCDwUAAEojnx4pVRzp6ekaPXq07r33XkVFRUmSDh06pCpVqnhsFxgYqJiYGB06dKjAtTIyMpSRkWFdTklJkSS5XC65XC5JksPhkNPplNvtljHG2raguNPplMPhyBPP\/t3pkJz6I+7Ovl2u3AqOOyQZj3j278YYK++Lyb24NWXHc+4zOy5Jbre7SPGAgAAZYzzi2bkUFKcmaqImaqImarK7ptzrlTXe6qHs7J94flITNVETNVETNZXtmoraP5WJoVRmZqbuueceGWM0ZcqUS15vwoQJGj9+fJ54YmKiIiIiJJ0\/9L1atWo6fPiwkpOTrW0qVaqkSpUqaf\/+\/UpLS7PisbGxio6O1q5du3Tu3Dkrnv2ANKgglQs9bcWTMsKVZZyqmyMmSTvSIxXocCsh5I+1XXLo9\/RIhTtdig8+Y8WTo6WdOt9s7tixw4qHh4erevXqOnHihI4dO2bFvVVTfHy8IiIilJiY6PFETEhIUGBgoEcuklS3bl1lZWUpKSnJijmdTtWrV09paWnat2+fFQ8ODlatWrWUnJzs0RRTEzVREzVREzX5qqayfPJvb\/ZQdvZPPD+piZqoiZqoiZrKdk1F7Z8cJueIzIccDofmzJmjO++80yOe3Uzt3LlTS5YsUcWKFa3rPvjgAz3++OM6efKkFcvKylJoaKg+\/\/xz9ezZM9995fdOX\/aDnP0OoremjklJSbp34GDVuu1RRVW+wop740iplCP7tfOrd\/XJ+1OUkJBwwRxL+yQ1Zy7+Mh2mJmqiJmqiprJfU0pKimJiYpScnGz1CaWJXT2Unf0Tz09qoiZqoiZqoqayXVNR+6dSfaRUdjO1Y8cOLV261KOZkqTWrVvr1KlT2rBhg6677jpJ0pIlS+R2u9WqVasC1w0JCVFISEieeEBAgAICAjxi2Xd4bkWNOxwOSZLbZA+WPLnzRAqLOzzi2b87HI48eRcnx4uN57fP4sYLyp2aqKmwODVREzVRU2Fxb9dU0O1Ks5Looezsn3Kufalxf39+FiVOTdRUUI7FjVMTNV1MnJouz5qK2j\/5dCiVmpqq33\/\/3bqclJSkzZs3KyYmRtWqVdOf\/vQnbdy4UfPnz5fL5bIOYYuJiVFwcLAaNGigrl27atCgQZo6daoyMzM1dOhQ9enTh2+NAQAAfoseCgAA+AOfDqXWr1+vm266ybr82GOPSZL69++vcePG6csvv5QkXXPNNR63W7p0qTp06CBJ+uijjzR06FB17NhRTqdTvXr10ltvvWVL\/gAAAL5ADwUAAPyBT4dSHTp08PgsY25FOd1VTEyMPv74Y2+mBQAAUKrRQwEAAH+Q\/4cJAQAAAAAAgBLEUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7Xw6lFqxYoVuv\/12xcXFyeFwaO7cuR7XG2P03HPPqVq1agoLC1OnTp20Y8cOj21OnDihvn37KioqStHR0Ro4cKBSU1NtrAIAAMBe9FAAAMAf+HQolZaWpqZNm+qdd97J9\/qJEyfqrbfe0tSpU7V27VqFh4erS5cuSk9Pt7bp27evfvnlFy1atEjz58\/XihUr9PDDD9tVAgAAgO3ooQAAgD8I9OXOu3Xrpm7duuV7nTFGkyZN0rPPPqsePXpIkj788ENVrVpVc+fOVZ8+fbR161YtWLBA69atU\/PmzSVJkydP1q233qrXXntNcXFxttUCAABgF3ooAADgD3w6lCpMUlKSDh06pE6dOlmx8uXLq1WrVlq9erX69Omj1atXKzo62mqmJKlTp05yOp1au3atevbsme\/aGRkZysjIsC6npKRIklwul1wulyTJ4XDI6XTK7XbLGGNtW1Dc6XTK4XDkiWf\/7nRITv0Rd2ffLlduBccdkoxHPPt3Y4yV98XkXtyasuM595kdlyS3212keEBAgIwxHvHsXAqKUxM1URM1URM12V1T7vVKu5Lqoezsn3h+UhM1URM1URM1le2aito\/ldqh1KFDhyRJVatW9YhXrVrVuu7QoUOqUqWKx\/WBgYGKiYmxtsnPhAkTNH78+DzxxMRERURESDrfvFWrVk2HDx9WcnKytU2lSpVUqVIl7d+\/X2lpaVY8NjZW0dHR2rVrl86dO2fFsx+QBhWkcqGnrXhSRriyjFN1c8QkaUd6pAIdbiWE\/LG2Sw79nh6pcKdL8cFnrHhytLRTUnp6usd5IsLDw1W9enWdOHFCx44ds+Leqik+Pl4RERFKTEz0eCImJCQoMDAwzzkr6tatq6ysLCUlJVkxp9OpevXqKS0tTfv27bPiwcHBqlWrlpKTkz0eQ2qiJmqiJmqiJl\/VVNbOs1RSPZSd\/RPPT2qiJmqiJmqiprJdU1H7J4fJOSLzIYfDoTlz5ujOO++UJK1atUpt27bVgQMHVK1aNWu7e+65Rw6HQ5999pleeuklzZw5U9u2bfNYq0qVKho\/frwGDx6c777ye6cv+0GOioqy8vHG1DEpKUn3DhysWrc9qqjKV1hxbxwplXJkv3Z+9a4+eX+KEhISLphjaZ+k5szFX6bD1ERN1ERN1FT2a0pJSVFMTIySk5OtPqE0sauHsrN\/4vlJTdRETdRETdRUtmsqav9Uao+Uio2NlSQdPnzYo6E6fPiwrrnmGmubI0eOeNwuKytLJ06csG6fn5CQEIWEhOSJBwQEKCAgwCOWfYfnVtS4w+GQJLlN9mDJkztPpLC4wyOe\/bvD4ciTd3FyvNh4fvssbryg3KmJmgqLUxM1URM1FRb3dk0F3a60Kqkeys7+Kefalxr39+dnUeLURE0F5VjcODVR08XEqenyrKmo\/VP+2ZQCCQkJio2N1eLFi61YSkqK1q5dq9atW0uSWrdurVOnTmnDhg3WNkuWLJHb7VarVq1szxkAAMDX6KEAAEBZ4dMjpVJTU\/X7779bl5OSkrR582bFxMSoRo0aGjFihF588UXVrVtXCQkJGjNmjOLi4qzD0xs0aKCuXbtq0KBBmjp1qjIzMzV06FD16dOHb40BAAB+ix4KAAD4A58OpdavX6+bbrrJuvzYY49Jkvr3768ZM2boySefVFpamh5++GGdOnVK7dq104IFCxQaGmrd5qOPPtLQoUPVsWNHOZ1O9erVS2+99ZbttQAAANiFHgoAAPiDUnOic19KSUlR+fLlS+QEpomJierz4CO6svujiqoS79W1U47s066v3tWnH0xV7dq1vbo2AAA4ryT7hLKM+wUAABSkqH1CqT2nFAAAAAAAAPwXQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHbFHkqdPXtWZ86csS7v3r1bkyZN0rfffuvVxAAAAPwJPRQAAICnYg+levTooQ8\/\/FCSdOrUKbVq1Up\/\/\/vf1aNHD02ZMsXrCQIAAPgDeigAAABPxR5Kbdy4UTfccIMk6YsvvlDVqlW1e\/duffjhh3rrrbe8niAAAIA\/oIcCAADwVOyh1JkzZxQZGSlJ+vbbb3XXXXfJ6XTq+uuv1+7du72eIAAAgD+ghwIAAPBU7KFUnTp1NHfuXO3du1cLFy5U586dJUlHjhxRVFSU1xMEAADwB\/RQAAAAnoo9lHruuef0xBNP6Morr1TLli3VunVrSeff8WvWrJnXEwQAAPAH9FAAAACeAot7gz\/96U9q166dDh48qKZNm1rxjh07qmfPnl5NDgAAwF\/QQwEAAHgq9pFSkhQbG6vIyEgtWrRIZ8+elSS1aNFC9evX92pyAAAA\/oQeCgAA4A\/FHkodP35cHTt2VL169XTrrbfq4MGDkqSBAwfq8ccf93qCAAAA\/oAeCgAAwFOxh1IjR45UUFCQ9uzZo3Llylnx3r17a8GCBV5NDgAAwF\/QQwEAAHgq9jmlvv32Wy1cuFDx8fEe8bp16\/J1xgAAAAWghwIAAPBU7COl0tLSPN7dy3bixAmFhIR4JSkAAAB\/Qw8FAADgqdhDqRtuuEEffvihddnhcMjtdmvixIm66aabvJocAACAv6CHAgAA8FTsj+9NnDhRHTt21Pr163Xu3Dk9+eST+uWXX3TixAl9\/\/33JZEjAABAmUcPBQAA4KnYR0o1atRI27dvV7t27dSjRw+lpaXprrvu0qZNm1S7du2SyBEAAKDMo4cCAADwVOwjpSSpfPny+utf\/+rtXAAAAPwaPRQAAMAfin2k1PTp0\/X555\/niX\/++eeaOXOmV5ICAADwN\/RQAAAAnoo9lJowYYIqVaqUJ16lShW99NJLXkkKAADA39BDAQAAeCr2UGrPnj1KSEjIE69Zs6b27NnjlaQAAAD8DT0UAACAp2IPpapUqaItW7bkif\/444+qWLGiV5ICAADwN\/RQAAAAnoo9lLr33ns1bNgwLV26VC6XSy6XS0uWLNHw4cPVp0+fksgRAACgzKOHAgAA8FTsb9974YUXtGvXLnXs2FGBgedv7na7df\/993M+BAAAgALQQwEAAHgq9lAqODhYn332mV544QX9+OOPCgsLU+PGjVWzZs2SyA8AAMAv0EMBAAB4KvZQKlu9evVUr149b+YCAADg9+ihAAAAziv2UMrlcmnGjBlavHixjhw5Irfb7XH9kiVLvJYcAACAv6CHAgAA8FTsodTw4cM1Y8YMde\/eXY0aNZLD4SiJvAAAAPwKPRQAAICnYg+lPv30U82aNUu33nprSeQDAADgl+ihiu\/o0aNKSUnx+rpRUVGqXLmy19cFAADFc1EnOq9Tp05J5AIAAOC36KGK5+jRo7pvwEM6cfqM19eOiSynf01\/j8EUAAA+Vuyh1OOPP64333xTb7\/9NoedAwAAFBE9VPGkpKToxOkzqty6l8Jjqnpt3bQTh3V09b+VkpLCUAoAAB8r9lBq5cqVWrp0qb755hs1bNhQQUFBHtfPnj3ba8kBAAD4C3qoixMeU1VRVeK9uuZRr64GAAAuVrGHUtHR0erZs2dJ5AIAAOC36KEAAAA8FXsoNX369JLIAwAAwK\/RQwEAAHhy+joBAAAAAAAAXH6KfaSUJH3xxReaNWuW9uzZo3Pnznlct3HjRq8kBgAA4G\/ooQAAAP5Q7COl3nrrLQ0YMEBVq1bVpk2b1LJlS1WsWFE7d+5Ut27dSiJHAACAMo8eCgAAwFOxh1Lvvvuupk2bpsmTJys4OFhPPvmkFi1apGHDhik5ObkkcgQAACjz6KEAAAA8FXsotWfPHrVp00aSFBYWptOnT0uS+vXrp08++cS72QEAAPgJeigAAABPxR5KxcbG6sSJE5KkGjVqaM2aNZKkpKQkGWO8mpzL5dKYMWOUkJCgsLAw1a5dWy+88ILHfowxeu6551StWjWFhYWpU6dO2rFjh1fzAAAAuFT0UAAAAJ6KPZS6+eab9eWXX0qSBgwYoJEjR+qWW25R79691bNnT68m98orr2jKlCl6++23tXXrVr3yyiuaOHGiJk+ebG0zceJEvfXWW5o6darWrl2r8PBwdenSRenp6V7NBQAA4FLQQwEAAHgq9rfvTZs2TW63W5I0ZMgQVaxYUatWrdIdd9yh\/\/u\/\/\/NqcqtWrVKPHj3UvXt3SdKVV16pTz75RD\/88IOk8+\/wTZo0Sc8++6x69OghSfrwww9VtWpVzZ07V3369PFqPgAAABeLHgoAAMBTsYdS+\/btU\/Xq1a3Lffr0UZ8+fWSM0d69e1WjRg2vJdemTRtNmzZN27dvV7169fTjjz9q5cqVev311yWdP9z90KFD6tSpk3Wb8uXLq1WrVlq9enWBDVVGRoYyMjKsyykpKZLOH+rucrkkSQ6HQ06nU2632+NQ94LiTqdTDocjTzz7d6dDcuqPuDv7drlyKzjukGQ84tm\/G2OsvC8m9+LWlB3Puc\/suCSr4b5QPCAgQMYYj3h2LgXFqYmaqImaqIma7K4p93oXq6z3UHb2T9mPTUCA06OHon+6PP7mqImaqImaqKns11TU\/qnYQ6mEhAQdPHhQVapU8YifOHFCCQkJXmvcJOmpp55SSkqK6tevr4CAALlcLv3tb39T3759JUmHDh2SJFWtWtXjdlWrVrWuy8+ECRM0fvz4PPHExERFRERIOt+YVatWTYcPH\/b4RpxKlSqpUqVK2r9\/v9LS0qx4bGysoqOjtWvXLp07d86KZz8gDSpI5UJPW\/GkjHBlGafq5ohJ0o70SAU63EoI+WNtlxz6PT1S4U6X4oPPWPHkaGmnpPT0dI9zQISHh6t69eo6ceKEjh07ZsW9VVN8fLwiIiKUmJjo8URMSEhQYGBgnvNR1K1bV1lZWUpKSrJiTqdT9erVU1pamvbt22fFg4ODVatWLSUnJ3s8htRETdRETdRETb6qKTU1Vd5Q1nsoO\/un+Ph4SVKra5upUoxDIf\/rl+ifLo+\/OWqiJmqiJmoq+zUVtX9ymGKeWdPpdOrw4cOqXLmyR3z37t26+uqrPYq+VJ9++qlGjRqlV199VQ0bNtTmzZs1YsQIvf766+rfv79WrVqltm3b6sCBA6pWrZp1u3vuuUcOh0OfffZZvuvm905f9oMcFRUlyXtTx6SkJN07cLBq3faooipfYcW98U5fypH92vnVu\/rk\/SlKSEi4YI6lfZKaMxd\/mQ5TEzVREzVRU9mvKSUlRTExMUpOTrb6hItR1nsoO\/snp9OpnTt3qu+gR1Wz2yNWD0X\/dHn8zVETNVETNVFT2a+pqP1TkY+Ueuyxx6wCx4wZo3LlylnXuVwurV27Vtdcc01RlyuSUaNG6amnnrIOIW\/cuLF2796tCRMmqH\/\/\/oqNjZUkHT582KOhOnz4cKG5hISEKCQkJE88ICBAAQEBHrHsOzy3osYdDockyW2yGyNP7jyRwuIOj3j27w6HI0\/excnxYuP57bO48YJypyZqKixOTdRETdRUWNzbNRV0u6Lylx7Kzv4pm8vlzreHon\/y77+5osSpiZoKyrG4cWqipouJU5P3+qciD6U2bdok6fzn73\/66ScFBwdb1wUHB6tp06Z64oknirpckZw5cybPHRYQEGBN3hISEhQbG6vFixdbDVRKSorWrl2rwYMHezUXAACAi0EPBQAAkL8iD6WWLl0q6fxXGL\/55puXdPh6Ud1+++3629\/+pho1aqhhw4batGmTXn\/9dT344IOSzk\/hRowYoRdffFF169ZVQkKCxowZo7i4ON15550lnh8AAMCF0EMBAADkr9gnOp8+fbrH5ZSUFC1ZskT169dX\/fr1vZaYJE2ePFljxozRo48+qiNHjiguLk7\/93\/\/p+eee87a5sknn1RaWpoefvhhnTp1Su3atdOCBQsUGhrq1VwAAAAuBT0UAACAp2IPpe655x7deOONGjp0qM6ePavmzZtr165dMsbo008\/Va9evbyWXGRkpCZNmqRJkyYVuI3D4dDzzz+v559\/3mv7BQAA8DZ6KAAAAE\/5n+GqECtWrNANN9wgSZozZ46MMTp16pTeeustvfjii15PEAAAwB\/QQwEAAHgq9lAqOTlZMTExkqQFCxaoV69eKleunLp3764dO3Z4PUEAAAB\/QA8FAADgqdhDqerVq2v16tVKS0vTggUL1LlzZ0nSyZMnOQcBAABAAeihAAAAPBX7nFIjRoxQ3759FRERoZo1a6pDhw6Szh+S3rhxY2\/nBwAA4BfooQAAADwVeyj16KOPqmXLltq7d69uueUWOZ3nD7aqVasW50MAAAAoAD0UAACAp2IPpSSpefPmat68uUese\/fuXkkIAADAX9FDAQAA\/KHYQymXy6UZM2Zo8eLFOnLkiNxut8f1S5Ys8VpyAAAA\/oIeCgAAwFOxh1LDhw\/XjBkz1L17dzVq1EgOh6Mk8gIAAPAr9FAAAACeij2U+vTTTzVr1izdeuutJZEPAACAX6KHAgAA8OQs7g2Cg4NVp06dksgFAADAb9FDAQAAeCr2UOrxxx\/Xm2++KWNMSeQDAADgl+ihAAAAPBX743srV67U0qVL9c0336hhw4YKCgryuH727NleSw4AAMBf0EMBAAB4KvZQKjo6Wj179iyJXAAAAPwWPRQAAICnYg+lpk+fXhJ5AAAA+DV6KAAAAE\/FPqcUAAAAAAAAcKmKdKTUtddeq8WLF6tChQpq1qyZHA5Hgdtu3LjRa8kBAACUZfRQAAAABSvSUKpHjx4KCQmRJN15550lmQ8AAIDfoIcCAAAoWJGGUmPHjs33dwAAABSMHgoAAKBgnFMKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtijSUSklJKek8AAAA\/A49FAAAQMGKNJSqUKGCjhw5Ikm6+eabderUqZLMCQAAwC\/QQwEAABSsSEOpiIgIHT9+XJK0bNkyZWZmlmhSAAAA\/oAeCgAAoGCBRdmoU6dOuummm9SgQQNJUs+ePRUcHJzvtkuWLPFedgAAAGUYPRQAAEDBijSU+te\/\/qWZM2cqMTFRy5cvV8OGDVWuXLmSzg0AAKBMo4cCAAAoWJGGUmFhYXrkkUckSevXr9crr7yi6OjokswLAACgzKOHAgAAKFiRhlI5LV261PrdGCNJcjgc3ssIAADAD9FDAQAAeCrSic5z+\/DDD9W4cWOFhYUpLCxMTZo00T\/\/+U9v5wYAAOBX6KEAAAD+UOwjpV5\/\/XWNGTNGQ4cOVdu2bSVJK1eu1COPPKJjx45p5MiRXk8SAACgrKOHAgAA8FTsodTkyZM1ZcoU3X\/\/\/VbsjjvuUMOGDTVu3DgaKgAAgHzQQwEAAHgq9sf3Dh48qDZt2uSJt2nTRgcPHvRKUgAAAP6GHgoAAMBTsYdSderU0axZs\/LEP\/vsM9WtW9crSQEAAPgbeigAAABPxf743vjx49W7d2+tWLHCOh\/C999\/r8WLF+fbaAEAAIAeCgAAILdiHynVq1cvrV27VpUqVdLcuXM1d+5cVapUST\/88IN69uxZEjkCAACUefRQAAAAnop9pJQkXXfddfrXv\/7l7VwAAAD8Gj0UAADAH4p9pBQAAAAAAABwqRhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2M5rQ6l3331Xzz\/\/vLeWAwAAuCzQQwEAgMuV14ZS\/\/73vzVjxgxvLQcAAHBZoIcCAACXK68NpRYvXqydO3d6aznL\/v37dd9996lixYoKCwtT48aNtX79eut6Y4yee+45VatWTWFhYerUqZN27Njh9TwAAABKAj0UAAC4XF3SUMoYI2OMt3LJ4+TJk2rbtq2CgoL0zTff6Ndff9Xf\/\/53VahQwdpm4sSJeuuttzR16lStXbtW4eHh6tKli9LT00ssLwAAgEtBDwUAAHCRQ6kPP\/xQjRs3VlhYmMLCwtSkSRP985\/\/9HZueuWVV1S9enVNnz5dLVu2VEJCgjp37qzatWtLOt\/QTZo0Sc8++6x69OihJk2a6MMPP9SBAwc0d+5cr+cDAABwKeihAAAA\/lDsodTrr7+uwYMH69Zbb9WsWbM0a9Ysde3aVY888ojeeOMNryb35Zdfqnnz5rr77rtVpUoVNWvWTP\/4xz+s65OSknTo0CF16tTJipUvX16tWrXS6tWrvZoLAADApaCHAgAA8BRY3BtMnjxZU6ZM0f3332\/F7rjjDjVs2FDjxo3TyJEjvZbczp07NWXKFD322GN65plntG7dOg0bNkzBwcHq37+\/Dh06JEmqWrWqx+2qVq1qXZefjIwMZWRkWJdTUlIkSS6XSy6XS5LkcDjkdDrldrs9Dq8vKO50OuVwOPLEs393OiSn\/oi7s2+XK7eC4w5JxiOe\/bsxxsr7YnIvbk3Z8Zz7zI5LktvtLlI8ICBAxhiPeHYuBcWpiZqoiZqoiZrsrin3eherrPdQdvZP2Y9NQIDTo4eif7o8\/uaoiZqoiZqoqezXVNT+qdhDqYMHD6pNmzZ54m3atNHBgweLu1yh3G63mjdvrpdeekmS1KxZM\/3888+aOnWq+vfvf9HrTpgwQePHj88TT0xMVEREhKTz7xZWq1ZNhw8fVnJysrVNpUqVVKlSJe3fv19paWlWPDY2VtHR0dq1a5fOnTvnUYMkNagglQs9bcWTMsKVZZyqmyMmSTvSIxXocCsh5I+1XXLo9\/RIhTtdig8+Y8WTo6WdktLT0z1OTBoeHq7q1avrxIkTOnbsmBX3Vk3x8fGKiIhQYmKixxMxISFBgYGBeU6SWrduXWVlZSkpKcmKOZ1O1atXT2lpadq3b58VDw4OVq1atZScnOzRFFMTNVETNVETNfmqptTUVHlDWe+h7Oyf4uPjJUmtrm2mSjEOhfyvX6J\/ujz+5qiJmqiJmqip7NdU1P7JYYp5ls1GjRrpz3\/+s5555hmP+IsvvqjPPvtMP\/30U3GWK1TNmjV1yy236L333rNiU6ZM0Ysvvqj9+\/dr586dql27tjZt2qRrrrnG2qZ9+\/a65ppr9Oabb+a7bn7v9GU\/yFFRUZK8N3VMSkrSvQMHq9Ztjyqq8hVW3Bvv9KUc2a+dX72rT96fooSEhAvmWNonqTlz8ZfpMDVREzVREzWV\/ZpSUlIUExOj5ORkq0+4GGW9h7Kzf3I6ndq5c6f6DnpUNbs9YvVQ9E+Xx98cNVETNVETNZX9moraPxX7SKnx48erd+\/eWrFihdq2bStJ+v7777V48WLNmjWruMsVqm3bttq2bZtHbPv27apZs6ak85O72NhYLV682GqoUlJStHbtWg0ePLjAdUNCQhQSEpInHhAQoICAAI9Y9h2eW1HjDodDkuQ22Y2RJ3eeSGFxh0c8+3eHw5En7+LkeLHx\/PZZ3HhBuVMTNRUWpyZqoiZqKizu7ZoKul1xlfUeys7+KZvL5c63h6J\/8u+\/uaLEqYmaCsqxuHFqoqaLiVOT9\/qnYg+levXqpbVr1+qNN96wvp2lQYMG+uGHH9SsWbPiLleokSNHqk2bNnrppZd0zz336IcfftC0adM0bdo0SecLHjFihF588UXVrVtXCQkJGjNmjOLi4nTnnXd6NRcAAIBLQQ8FAADgqdhDKUm67rrr9K9\/\/cvbueTRokULzZkzR08\/\/bSef\/55JSQkaNKkSerbt6+1zZNPPqm0tDQ9\/PDDOnXqlNq1a6cFCxYoNDS0xPMDAAAoDnooAACAP1zUUMpOt912m2677bYCr3c4HHr++ef1\/PPP25gVAABA6UYPBQAASrsiD6WyT35VGIfDoaysrEtOCgAAwF\/QQwEAAOSvyEOpOXPmFHjd6tWr9dZbb+U5+zoAAMDljh4KAAAgf0UeSvXo0SNPbNu2bXrqqac0b9489e3bl8O\/AQAAcqGHAgAAyF\/+3wV4AQcOHNCgQYPUuHFjZWVlafPmzZo5c6b1NcMAAADIix4KAADgD8U60XlycrJeeuklTZ48Wddcc40WL16sG264oaRywyU4evSoUlJSvL5uVFSUKleu7PV1AQDwZ\/RQAAAAeRV5KDVx4kS98sorio2N1SeffJLvoegoHY4ePar7BjykE6fPeH3tmMhy+tf09xhMAQBQRPRQAAAA+SvyUOqpp55SWFiY6tSpo5kzZ2rmzJn5bjd79myvJYeLk5KSohOnz6hy614Kj6nqtXXTThzW0dX\/VkpKCkMpAACKiB4KAAAgf0UeSt1\/\/\/0X\/DpjlC7hMVUVVSXeq2se9epqAAD4P3ooAACA\/BV5KDVjxowSTAMAAMA\/0UMBAADk76K+fQ8AAAAAAAC4FAylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwXZkaSr388styOBwaMWKEFUtPT9eQIUNUsWJFRUREqFevXjp8+LDvkgQAAChl6KEAAEBpVGaGUuvWrdP\/+3\/\/T02aNPGIjxw5UvPmzdPnn3+u5cuX68CBA7rrrrt8lCUAAEDpQg8FAABKqzIxlEpNTVXfvn31j3\/8QxUqVLDiycnJev\/99\/X666\/r5ptv1nXXXafp06dr1apVWrNmjQ8zBgAA8D16KAAAUJqViaHUkCFD1L17d3Xq1MkjvmHDBmVmZnrE69evrxo1amj16tV2pwkAAFCq0EMBAIDSLNDXCVzIp59+qo0bN2rdunV5rjt06JCCg4MVHR3tEa9ataoOHTpU4JoZGRnKyMiwLqekpEiSXC6XXC6XJMnhcMjpdMrtdssYY21bUNzpdMrhcOSJZ\/\/udEhO\/RF3Z98uV24Fxx2SjEc8+3djjJW3JLnd51dxyHOfRpKRQw4ZOXKsU1A8e5XsuNMhBQQ4rZpy7jP7Psi5\/wvFAwICZIzxiGffvwXFi\/p4FPdxyo5TEzVREzVREzXlrin3emWFt3soO\/un7McmIMDp0UOVZP9UVp+fOXPxl785aqImaqImair7NRW1fyrVQ6m9e\/dq+PDhWrRokUJDQ7227oQJEzR+\/Pg88cTEREVEREiSypcvr2rVqunw4cNKTk62tqlUqZIqVaqk\/fv3Ky0tzYrHxsYqOjpau3bt0rlz56x49gPSoIJULvS0FU\/KCFeWcapujpgk7UiPVKDDrYSQP9Z2yaHf0yMV7nQpPviMFU+Olnbq\/IlKd+zYYcVTU1MlSVXCpBo51j\/lCtbhzFBVCcpQdMAfOR7LCtHxrBBdEXxW4c4sK34oM1TJrmDVDDmjEIdLGTEOxbdsbtWXmJjo8URMSEhQYGCgRy6SVLduXWVlZSkpKcmKOZ1O1atXT2lpadq3b58VDw4OVq1atZScnOzRFIeHh6t69eo6ceKEjh07ZsW99TjFx8crIiKCmqiJmqiJmqgpT03Zr6tlSUn0UHb2T\/Hx8ZKkVtc2U6UYh0L+18+UZP9UVp+fkv\/9zVETNVETNVFT2a+pqP2Tw+QckZUyc+fOVc+ePRUQEGDFXC6XNflbuHChOnXqpJMnT3q801ezZk2NGDFCI0eOzHfd\/N7py36Qo6KiJHlv6piUlKR7Bw5WrdseVVTlK6y4N97pSzmyXzu\/elefvD9FCQkJVnznzp3680OPKqH7oypf5Y99XuqRUilH92v3N1P1r2nvqE6dOkyHqYmaqImaqOmyqCklJUUxMTFKTk62+oTSriR6KDv7J6fTqZ07d6rvoEdVs9sjVg9Vkv1TWX1+5szFX\/7mqImaqImaqKns11TU\/qlUHynVsWNH\/fTTTx6xAQMGqH79+ho9erSqV6+uoKAgLV68WL169ZIkbdu2TXv27FHr1q0LXDckJEQhISF54gEBAR7Nm\/THHZ5bUeMOx\/kxj9tkN0ae3HkihcUdHvHs3x0Oh0fe2TkY5b9PI0eOD\/UVPe42ksvltmrKfV9lK048d+4Xil\/q43GhODVREzVRU2Fxaro8ayrodqVZSfRQdvZP2Vwud749VEn0Txebo6+fn0WJUxM1FZRjcePURE0XE6emy7OmovZPpXooFRkZqUaNGnnEwsPDVbFiRSs+cOBAPfbYY4qJiVFUVJT+8pe\/qHXr1rr++ut9kTIAAIDP0UMBAICyoFQPpYrijTfekNPpVK9evZSRkaEuXbro3Xff9XVaAAAApRo9FAAA8LUyN5RatmyZx+XQ0FC98847euedd3yTEAAAQBlADwUAAEqb\/D9MCAAAAAAAAJQghlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbFeqh1ITJkxQixYtFBkZqSpVqujOO+\/Utm3bPLZJT0\/XkCFDVLFiRUVERKhXr146fPiwjzIGAADwPXooAABQFpTqodTy5cs1ZMgQrVmzRosWLVJmZqY6d+6stLQ0a5uRI0dq3rx5+vzzz7V8+XIdOHBAd911lw+zBgAA8C16KAAAUBYE+jqBwixYsMDj8owZM1SlShVt2LBBN954o5KTk\/X+++\/r448\/1s033yxJmj59uho0aKA1a9bo+uuv90XaAAAAPkUPBQAAyoJSPZTKLTk5WZIUExMjSdqwYYMyMzPVqVMna5v69eurRo0aWr16dYENVUZGhjIyMqzLKSkpkiSXyyWXyyVJcjgccjqdcrvdMsZY2xYUdzqdcjgceeLZvzsdklN\/xN3Zt8uVW8FxhyTjEc\/+3Rhj5S1Jbvf5VRzy3KeRZOSQQ0aOHOsUFM9eJTvudEgBAU6rppz7zL4Pcu7\/QvGAgAAZYzzi2fdvQfGiPh7FfZyy49RETdRETdRETblryr1eWeSNHsrO\/in7sQkIcHr0UCXZP5XV52fOXPzlb46aqImaqImayn5NRe2fysxQyu12a8SIEWrbtq0aNWokSTp06JCCg4MVHR3tsW3VqlV16NChAteaMGGCxo8fnyeemJioiIgISVL58uVVrVo1HT582GrkJKlSpUqqVKmS9u\/f73EIfGxsrKKjo7Vr1y6dO3fOI29JalBBKhd62oonZYQryzhVN0dMknakRyrQ4VZCyB9ru+TQ7+mRCne6FB98xoonR0s7df6cEDt27LDiqampkqQqYVKNHOufcgXrcGaoqgRlKDrgjxyPZYXoeFaIrgg+q3BnlhU\/lBmqZFewaoacUYjDpYwYh+JbNrfqS0xM9HgiJiQkKDAw0CMXSapbt66ysrKUlJRkxZxOp+rVq6e0tDTt27fPigcHB6tWrVpKTk72eAzDw8NVvXp1nThxQseOHbPi3nqc4uPjFRERQU3URE3URE3UlKem7NfVsspbPZSd\/VN8fLwkqdW1zVQpxqGQ\/\/UzJdk\/ldXnp+R\/f3PURE3URE3UVPZrKmr\/5DA5R2Sl2ODBg\/XNN99o5cqVVqPy8ccfa8CAAR7v2klSy5YtddNNN+mVV17Jd6383unLfpCjoqIkeW\/qmJSUpHsHDlat2x5VVOUrrLg33ulLObJfO796V5+8P0UJCQlWfOfOnfrzQ48qofujKl\/lj31e6pFSKUf3a\/c3U\/Wvae+oTp06TIepiZqoiZqo6bKoKSUlRTExMUpOTrb6hLLEWz2Unf2T0+nUzp071XfQo6rZ7RGrhyrJ\/qmsPj9z5uIvf3PURE3URE3UVPZrKmr\/VCaOlBo6dKjmz5+vFStWWM2UdH7Sd+7cOZ06dcrjnb7Dhw8rNja2wPVCQkIUEhKSJx4QEKCAgACPWPYdnltR4w7H+TGP22Q3Rp7ceSKFxR0e8ezfHQ6HR97ZORjlv08jR44P9RU97jaSy+W2asp9X2UrTjx37heKX+rjcaE4NVETNVFTYXFqujxrKuh2ZYE3eyg7+6dsLpc73x6qJPqni83R18\/PosSpiZoKyrG4cWqipouJU9PlWVNR+6f8sykljDEaOnSo5syZoyVLlni8myVJ1113nYKCgrR48WIrtm3bNu3Zs0etW7e2O10AAIBSgR4KAACUBaX6SKkhQ4bo448\/1n\/+8x9FRkZan6ssX768wsLCVL58eQ0cOFCPPfaYYmJiFBUVpb\/85S9q3bo13xoDAAAuW\/RQAACgLCjVQ6kpU6ZIkjp06OARnz59uh544AFJ0htvvCGn06levXopIyNDXbp00bvvvmtzpgAAAKUHPRQAACgLSvVQqijnYA8NDdU777yjd955x4aMAAAASj96KAAAUBaU6nNKAQAAAAAAwD8xlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUAAAAAAADbMZQCAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAgAAAAAAgO0YSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsF+joBAAAAoDQ4evSoUlJSSmTtqKgoVa5cuUTWBgCgrGIoBQAAgMve0aNHdd+Ah3Ti9JkSWT8mspz+Nf09BlMAAOTAUAoAAACXvZSUFJ04fUaVW\/dSeExVr66dduKwjq7+t1JSUhhKAQCQA0MpeEVJHe5eWg5153B+AAAuD+ExVRVVJd7r6x71+ooAAJR9DKVwyUrycPfScKg7h\/MDAAAAAOB9DKVwyUrqcPfScqg7h\/MDAAAAAOB9DKXgNSVxuHtpOtSdw\/kBAAAAAPAep68TAAAAAAAAwOWHoRQAAAAAAABsx8f3gFLK37\/R0G58gyIAAAAAlC4MpYBSyN+\/0dBufIMiAAAAAJQ+DKWAUsjfv9HQbnyDIlA6cMQi4Im\/CQDA5Y6hFFCK+fs3GtqNb1AEfIcjFgFP\/E0AAMBQCgAA2IAjFgFP\/E0AAMBQCgAA2IgjFgFP\/E2gtOPLd8o+HkOUZgylAAAAAAB58OU7ZR+PIUo7hlIAAAAAgDz48p2yj8cQpR1DKQDwExya7V2Xw7diXQ41AvBk92sFr03+gS\/fKft4DFFaMZQCAD\/AodnedTl8K9blUCMAT3a\/VvDaBAC4EL8ZSr3zzjt69dVXdejQITVt2lSTJ09Wy5YtfZ0WSgjv7nufv7xzWtg+\/RmHZnvX5fCtWJdDjSgaeqjLh92vFb54baK\/QGnHc9T77L5PffEY+vNRp34xlPrss8\/02GOPaerUqWrVqpUmTZqkLl26aNu2bapSpYqv04OX8e6+9\/nTO6cF7fNywaHZ3nU5fCvW5VAjCkYPdXmy+7XCrv3RX6C04znqfXbfp754DP39qFO\/GEq9\/vrrGjRokAYMGCBJmjp1qr766it98MEHeuqpp3ycHbyNd\/e9z1\/eOS1snwCAvOih4E\/oL1Da8Rz1PrvvU188hv7+iYgyP5Q6d+6cNmzYoKefftqKOZ1OderUSatXr873NhkZGcrIyLAuJycnS5JOnjwpl8slSXI4HHI6nXK73TLGWNsWFHc6nXI4HHniKSkpcmVlKeXQLrky\/phsuv+3idPhmVtx4mknj5xfOyVFJ0+ezLPP5IOe+zRGMpIckhw51smOO\/W\/KwuIp508ImPcSklJOb+P\/91XKSkpMsatUwd3KTP9zCXVJCO5\/5fGmVN\/7O\/UqVPW\/Z69P9e5s8pKP3NJNeXOxXXurLXPkydPyul0WvvL+RhebE2OXPHTJ4\/I7XJ5PIYOh0OnT5+WcXvu82JrKs5zJjPjrMdz5mJqyhnPeX+mpKRYfx\/Z92lWxtnzz5lLqCl3POc+s\/+2cz+Gl1JT7hzP5nienjx50uPfiJMnT+rUqVPWbRwOh8e\/DxeKF6RChQoqX768R+z06dN5\/625yJpyxtP+9xw9ffq0Tp065ZFncnJyntjF1pRbdHS0KlasKGOM3G63JOnUqVM6depUse\/HosSjo6MVHR1t\/VtepOeMLu7f8pz\/luZ8zhhjdOLEiUt6zhQUr1ChgqKjo336+pSSkiLjPv9akZV+5oLPvZzxi319yuZ0Os\/n+r\/n0oXiAQEBHs+97MPlL+U5XRoVt4eys39yOp3nXwsv5fW3gLjd\/VPOfZ4+fdrzb6IE+idHPn8TuV9\/Uw6d36e3+qfcr4XZf1uX9G\/pJfRPrnNnvdo\/STrfI+XzvElOTva4nM0b\/35nvxbm\/vu4mNfforwu53wtlOTRd2c\/Z6Sy2z\/lrDFbQECATpw4kecxLKnX35SUFLldrvPPp\/Qzxe5zC4tn98CnT59WcnKyx2tYQa+\/xekJc8adktJyPIbJycke\/5Zn92yF3TfFkV\/Plv2cyfl\/Q1fGmUuqKfe\/EZkZZ8\/\/nyxXP+PKyvL4d0byzuuT61z+\/85k7zMr1\/\/VLvX1Kff\/1XzWP5kybv\/+\/UaSWbVqlUd81KhRpmXLlvneZuzYsUbnHw9++OGHH3744YefIv3s3bvXjtbGNsXtoeif+OGHH3744Yef4v5cqH8q80dKXYynn35ajz32mHXZ7XbrxIkTqlixohwORyG3LHkpKSmqXr269u7dq6ioKJ\/mUhL8vT7J\/2v09\/ok\/6\/R3+uT\/L9G6rOXMUanT59WXFycr1PxKfon3\/L3Gv29Psn\/a\/T3+iT\/r9Hf65P8v8bSVF9R+6cyP5SqVKmSAgICdPjwYY\/44cOHFRsbm+9tQkJCFBIS4hHLeRhnaRAVFeXzJ1FJ8vf6JP+v0d\/rk\/y\/Rn+vT\/L\/GqnPPrk\/MusPittD0T+VDv5eo7\/XJ\/l\/jf5en+T\/Nfp7fZL\/11ha6itK\/+S0IY8SFRwcrOuuu06LFy+2Ym63W4sXL1br1q19mBkAAEDpRQ8FAAB8rcwfKSVJjz32mPr376\/mzZurZcuWmjRpktLS0qxvkgEAAEBe9FAAAMCX\/GIo1bt3bx09elTPPfecDh06pGuuuUYLFixQ1are\/YpGO4SEhGjs2LF5Do\/3F\/5en+T\/Nfp7fZL\/1+jv9Un+XyP1wVv8pYe6HJ4z\/l6jv9cn+X+N\/l6f5P81+nt9kv\/XWBbrcxjjZ99vDAAAAAAAgFKvzJ9TCgAAAAAAAGUPQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKFWKvPPOO7ryyisVGhqqVq1a6YcffvB1Sl4zYcIEtWjRQpGRkapSpYruvPNObdu2zddplZiXX35ZDodDI0aM8HUqXrV\/\/37dd999qlixosLCwtS4cWOtX7\/e12l5hcvl0pgxY5SQkKCwsDDVrl1bL7zwgsryd0GsWLFCt99+u+Li4uRwODR37lyP640xeu6551StWjWFhYWpU6dO2rFjh2+SvQiF1ZeZmanRo0ercePGCg8PV1xcnO6\/\/34dOHDAdwlfhAs9hjk98sgjcjgcmjRpkm35Xaqi1Ld161bdcccdKl++vMLDw9WiRQvt2bPH\/mRRqvlrD0X\/5B\/8uX+S\/K+H8vf+SfL\/Hsrf+yfJv3oohlKlxGeffabHHntMY8eO1caNG9W0aVN16dJFR44c8XVqXrF8+XINGTJEa9as0aJFi5SZmanOnTsrLS3N16l53bp16\/T\/\/t\/\/U5MmTXydiledPHlSbdu2VVBQkL755hv9+uuv+vvf\/64KFSr4OjWveOWVVzRlyhS9\/fbb2rp1q1555RVNnDhRkydP9nVqFy0tLU1NmzbVO++8k+\/1EydO1FtvvaWpU6dq7dq1Cg8PV5cuXZSenm5zphensPrOnDmjjRs3asyYMdq4caNmz56tbdu26Y477vBBphfvQo9htjlz5mjNmjWKi4uzKTPvuFB9iYmJateunerXr69ly5Zpy5YtGjNmjEJDQ23OFKWZP\/dQ9E9ln7\/3T5L\/9VD+3j9J\/t9D+Xv\/JPlZD2VQKrRs2dIMGTLEuuxyuUxcXJyZMGGCD7MqOUeOHDGSzPLly32diledPn3a1K1b1yxatMi0b9\/eDB8+3Ncpec3o0aNNu3btfJ1Gienevbt58MEHPWJ33XWX6du3r48y8i5JZs6cOdZlt9ttYmNjzauvvmrFTp06ZUJCQswnn3zigwwvTe768vPDDz8YSWb37t32JOVlBdW4b98+c8UVV5iff\/7Z1KxZ07zxxhu25+YN+dXXu3dvc9999\/kmIZQZl1MPRf9U9vh7\/2SMf\/dQ\/t4\/GeP\/PZS\/90\/GlP0eiiOlSoFz585pw4YN6tSpkxVzOp3q1KmTVq9e7cPMSk5ycrIkKSYmxseZeNeQIUPUvXt3j8fSX3z55Zdq3ry57r77blWpUkXNmjXTP\/7xD1+n5TVt2rTR4sWLtX37dknSjz\/+qJUrV6pbt24+zqxkJCUl6dChQx7P1fLly6tVq1Z+\/e+Ow+FQdHS0r1PxGrfbrX79+mnUqFFq2LChr9PxKrfbra+++kr16tVTly5dVKVKFbVq1arQQ\/Bx+bnceij6p7LH3\/sn6fLqoS7H\/knyvx7Kn\/snqez1UAylSoFjx47J5XKpatWqHvGqVavq0KFDPsqq5Ljdbo0YMUJt27ZVo0aNfJ2O13z66afauHGjJkyY4OtUSsTOnTs1ZcoU1a1bVwsXLtTgwYM1bNgwzZw509epecVTTz2lPn36qH79+goKClKzZs00YsQI9e3b19eplYjsf1sul3930tPTNXr0aN17772KiorydTpe88orrygwMFDDhg3zdSped+TIEaWmpurll19W165d9e2336pnz5666667tHz5cl+nh1Licuqh6J\/KJn\/vn6TLq4e63PonyT97KH\/un6Sy10MF+joBXH6GDBmin3\/+WStXrvR1Kl6zd+9eDR8+XIsWLSqdn9P1ArfbrebNm+ull16SJDVr1kw\/\/\/yzpk6dqv79+\/s4u0s3a9YsffTRR\/r444\/VsGFDbd68WSNGjFBcXJxf1Hc5y8zM1D333CNjjKZMmeLrdLxmw4YNevPNN7Vx40Y5HA5fp+N1brdbktSjRw+NHDlSknTNNddo1apVmjp1qtq3b+\/L9ADb0T+VTf7eP0n0UP7MH3sof++fpLLXQ3GkVClQqVIlBQQE6PDhwx7xw4cPKzY21kdZlYyhQ4dq\/vz5Wrp0qeLj432djtds2LBBR44c0bXXXqvAwEAFBgZq+fLleuuttxQYGCiXy+XrFC9ZtWrVdPXVV3vEGjRoUCq\/weFijBo1ynqnr3HjxurXr59Gjhzpt+\/cZv\/b4u\/\/7mQ3U7t379aiRYv85h0+Sfruu+905MgR1ahRw\/p3Z\/fu3Xr88cd15ZVX+jq9S1apUiUFBgb69b87uHSXSw9F\/1R2+Xv\/JF1ePdTl0j9J\/ttD+Xv\/JJW9HoqhVCkQHBys6667TosXL7ZibrdbixcvVuvWrX2YmfcYYzR06FDNmTNHS5YsUUJCgq9T8qqOHTvqp59+0ubNm62f5s2bq2\/fvtq8ebMCAgJ8neIla9u2bZ6vod6+fbtq1qzpo4y868yZM3I6Pf9JDAgIsN5p8DcJCQmKjY31+HcnJSVFa9eu9Zt\/d7KbqR07dui\/\/\/2vKlas6OuUvKpfv37asmWLx787cXFxGjVqlBYuXOjr9C5ZcHCwWrRo4df\/7uDS+XsPRf9E\/1QWXE491OXQP0n+3UP5e\/8klb0eio\/vlRKPPfaY+vfvr+bNm6tly5aaNGmS0tLSNGDAAF+n5hVDhgzRxx9\/rP\/85z+KjIy0PnNdvnx5hYWF+Ti7SxcZGZnn\/A7h4eGqWLGi35z3YeTIkWrTpo1eeukl3XPPPfrhhx80bdo0TZs2zdepecXtt9+uv\/3tb6pRo4YaNmyoTZs26fXXX9eDDz7o69QuWmpqqn7\/\/XfrclJSkjZv3qyYmBjVqFFDI0aM0Isvvqi6desqISFBY8aMUVxcnO68807fJV0MhdVXrVo1\/elPf9LGjRs1f\/58uVwu69+dmJgYBQcH+yrtYrnQY5i7SQwKClJsbKyuuuoqu1O9KBeqb9SoUerdu7duvPFG3XTTTVqwYIHmzZunZcuW+S5plDr+3EPRP5V9\/t4\/Sf7XQ\/l7\/yT5fw\/l7\/2T5Gc9lG+\/\/A85TZ482dSoUcMEBwebli1bmjVr1vg6Ja+RlO\/P9OnTfZ1aifG3rzQ2xph58+aZRo0amZCQEFO\/fn0zbdo0X6fkNSkpKWb48OGmRo0aJjQ01NSqVcv89a9\/NRkZGb5O7aItXbo037+7\/v37G2POf63xmDFjTNWqVU1ISIjp2LGj2bZtm2+TLobC6ktKSirw352lS5f6OvUiu9BjmFtZ+0rjotT3\/vvvmzp16pjQ0FDTtGlTM3fuXN8ljFLLX3so+if\/4M\/9kzH+10P5e\/9kjP\/3UP7ePxnjXz2UwxhjLn20BQAAAAAAABQd55QCAAAAAACA7RhKAQAAAAAAwHYMpQAAAAAAAGA7hlIAAAAAAACwHUMpAAAAAAAA2I6hFAAAAAAAAGzHUAoAAAAAAAC2YygFAAAAAAAA2zGUAi5DZ86cUa9evRQVFSWHw6FTp07l2WbcuHG65pprbM\/Nl3bt2iWHw6HNmzf7OpUi69Chg0aMGGFdvvLKKzVp0iTb85gxY4aio6MLvL4o9+2yZcsKfD4CAFAa0EPljx7q4tFD4XLHUAqwwQMPPCCHw6GXX37ZIz537lw5HA7b85k5c6a+++47rVq1SgcPHlT58uXzbPPEE09o8eLFtudmlwceeEB33nmnr9PwunXr1unhhx8u0rYXaoLs1qZNG4\/nY2nLDwBgP3qo0oceqvT1KPRQKMsYSgE2CQ0N1SuvvKKTJ0\/6OhUlJiaqQYMGatSokWJjY\/Nt6iIiIlSxYkUfZPeHc+fO5YkZY5SVleWDbEpOfnVerMqVK6tcuXJeW89OwcHBBT4fAQCXL3qo4qOHKj56KMA3GEoBNunUqZNiY2M1YcKEQrf797\/\/rYYNGyokJERXXnml\/v73vxd7X4Wt0aFDB\/3973\/XihUr5HA41KFDh3zXyH3oefa7Yq+99pqqVaumihUrasiQIcrMzLS2ycjI0OjRo1W9enWFhISoTp06ev\/9963rly9frpYtWyokJETVqlXTU0895dEcdejQQUOHDtWIESNUqVIldenSxToc+ZtvvtF1112nkJAQrVy5Um63WxMmTFBCQoLCwsLUtGlTffHFFx41\/PLLL7rtttsUFRWlyMhI3XDDDUpMTNS4ceM0c+ZM\/ec\/\/5HD4ZDD4dCyZcs8bmuMUZ06dfTaa695xDdv3iyHw6Hff\/893\/st+34aP368KleurKioKD3yyCMeTVN+dUrSzz\/\/rG7duikiIkJVq1ZVv379dOzYMet2aWlpuv\/++xUREaFq1arl+9zIfej5qVOn9H\/\/93+qWrWqQkND1ahRI82fP1\/Lli3TgAEDlJycbN0H48aNsx7HJ554QldccYXCw8PVqlWrPPfPjBkzVKNGDZUrV049e\/bU8ePH870\/cvvtt9\/Upk0bK5fly5db1+U89Lyw\/N59913VrVtXoaGhqlq1qv70pz8Vad8AgLKJHooeqrA6JXooeiiUaQZAievfv7\/p0aOHmT17tgkNDTV79+41xhgzZ84ck\/PPcP369cbpdJrnn3\/ebNu2zUyfPt2EhYWZ6dOnF3lfF1rj+PHjZtCgQaZ169bm4MGD5vjx4\/muM3bsWNO0aVOPGqKioswjjzxitm7daubNm2fKlStnpk2bZm1zzz33mOrVq5vZs2ebxMRE89\/\/\/td8+umnxhhj9u3bZ8qVK2ceffRRs3XrVjNnzhxTqVIlM3bsWOv27du3NxEREWbUqFHmt99+M7\/99ptZunSpkWSaNGlivv32W\/P777+b48ePmxdffNHUr1\/fLFiwwCQmJprp06ebkJAQs2zZMmt\/MTEx5q677jLr1q0z27ZtMx988IH57bffzOnTp80999xjunbtag4ePGgOHjxoMjIyTFJSkpFkNm3aZIwx5m9\/+5u5+uqrPe6XYcOGmRtvvLHA+79\/\/\/4mIiLC9O7d2\/z8889m\/vz5pnLlyuaZZ54ptM6TJ0+aypUrm6efftps3brVbNy40dxyyy3mpptusm43ePBgU6NGDfPf\/\/7XbNmyxdx2220mMjLSDB8+3NqmZs2a5o033jDGGONyucz1119vGjZsaL799luTmJho5s2bZ77++muTkZFhJk2aZKKioqz74PTp08YYYx566CHTpk0bs2LFCvP777+bV1991YSEhJjt27cbY4xZs2aNcTqd5pVXXjHbtm0zb775pomOjjbly5cv8H7Jvm\/j4+PNF198YX799Vfz0EMPmcjISHPs2DFjjLEe65MnTxaY37p160xAQID5+OOPza5du8zGjRvNm2++WeB+AQBlGz0UPRQ9FD0U\/BtDKcAG2Q2VMcZcf\/315sEHHzTG5G2o\/vznP5tbbrnF47ajRo3K86JemKKsMXz4cNO+fftC18mvoapZs6bJysqyYnfffbfp3bu3McaYbdu2GUlm0aJF+a73zDPPmKuuusq43W4r9s4775iIiAjjcrmMMecbjWbNmnncLvtFdu7cuVYsPT3dlCtXzqxatcpj24EDB5p7773XGGPM008\/bRISEsy5c+fyzSfnY5Itd0O1f\/9+ExAQYNauXWuMMebcuXOmUqVKZsaMGfmumb1uTEyMSUtLs2JTpky5YJ0vvPCC6dy5s0ds7969RpLZtm2bOX36tAkODjazZs2yrj9+\/LgJCwsrsKFauHChcTqdZtu2bfnmOn369DxN0O7du01AQIDZv3+\/R7xjx47m6aefNsYYc++995pbb73V4\/revXsXqaF6+eWXrVhmZqaJj483r7zyijHGs6EqKL9\/\/\/vfJioqyqSkpBS4LwCA\/6CHooeih6KHgn\/j43uAzV555RXNnDlTW7duzXPd1q1b1bZtW49Y27ZttWPHDrlcriKt7401CtKwYUMFBARYl6tVq6YjR45IOn9IdkBAgNq3b19gXq1bt\/b4rHvbtm2Vmpqqffv2WbHrrrsu39s3b97c+v3333\/XmTNndMsttygiIsL6+fDDD5WYmGjlc8MNNygoKOii642Li1P37t31wQcfSJLmzZunjIwM3X333YXermnTph7nJGjdurVSU1O1d+\/eAuv88ccftXTpUo966tevL+n8+SsSExN17tw5tWrVyrpNTEyMrrrqqgLz2Lx5s+Lj41WvXr0i1\/zTTz\/J5XKpXr16HrksX77cum+3bt3qkUd2jUWRc7vAwEA1b94837+Fgtxyyy2qWbOmatWqpX79+umjjz7SmTNninx7AEDZRQ9FD5VfnfRQRUMPhdIq0NcJAJebG2+8UV26dNHTTz+tBx54wNfpFEvu5sThcMjtdkuSwsLCvLKP8PDwC8ZTU1MlSV999ZWuuOIKj+1CQkK8ms9DDz2kfv366Y033tD06dPVu3dvr5wEM3edqampuv322\/XKK6\/k2bZatWoFnn+hMBdzH6SmpiogIEAbNmzwaJ6l8ydu9bXIyEht3LhRy5Yt07fffqvnnntO48aN07p16\/iWGQDwc\/RQhaOHoocqDD0USiuOlAJ84OWXX9a8efO0evVqj3iDBg30\/fffe8S+\/\/571atXL8+LW0G8scbFaNy4sdxut8dJF3PntXr1ahljPPKKjIxUfHx8sfZ19dVXKyQkRHv27FGdOnU8fqpXry5JatKkib777juPk4jmFBwcXKR3PW+99VaFh4drypQpWrBggR588MEL3ubHH3\/U2bNnrctr1qxRRESElVt+rr32Wv3yyy+68sor89QUHh6u2rVrKygoSGvXrrVuc\/LkSW3fvr3ANZs0aaJ9+\/YVuE1+90GzZs3kcrl05MiRPHnExsZKOv9Y5swju8aiyLldVlaWNmzYoAYNGhQ5P+n8u4OdOnXSxIkTtWXLFu3atUtLliwp0v4BAGUbPdQfedFDnUcPVbT8JHoolE4MpQAfaNy4sfr27au33nrLI\/74449r8eLFeuGFF7R9+3bNnDlTb7\/9tp544glrm44dO+rtt98ucO2irFESrrzySvXv318PPvig5s6dq6SkJC1btkyzZs2SJD366KPau3ev\/vKXv+i3337Tf\/7zH40dO1aPPfaYnM7i\/VMUGRmpJ554QiNHjtTMmTOVmJiojRs3avLkyZo5c6YkaejQoUpJSVGfPn20fv167dixQ\/\/85z+1bds2K98tW7Zo27ZtOnbsWIGNV0BAgB544AE9\/fTTqlu3bpEOsT537pwGDhyoX3\/9VV9\/\/bXGjh2roUOHFlrnkCFDdOLECd17771at26dEhMTtXDhQg0YMEAul0sREREaOHCgRo0apSVLlujnn3\/WAw88UOia7du314033qhevXpp0aJFSkpK0jfffKMFCxZY90FqaqoWL16sY8eO6cyZM6pXr5769u2r+++\/X7Nnz1ZSUpJ++OEHTZgwQV999ZUkadiwYVqwYIFee+017dixQ2+\/\/ba15oW88847mjNnjn777TcNGTJEJ0+eLLBJzS+\/+fPn66233tLmzZu1e\/duffjhh3K73YUegg8A8B\/0UPRQudFD5UUPhTLF1ye1Ai4HBZ0QMjg42OT+M\/ziiy\/M1VdfbYKCgkyNGjXMq6++6nF9zZo1Pb5tJT8XWuNiT9KZu4bc65w9e9aMHDnSVKtWzQQHB5s6deqYDz74wLp+2bJlpkWLFiY4ONjExsaa0aNHm8zMTOv69u3be5xw0pi8J27M5na7zaRJk8xVV11lgoKCTOXKlU2XLl3M8uXLrW1+\/PFH07lzZ1OuXDkTGRlpbrjhBpOYmGiMMebIkSPmlltuMREREUaSWbp0aZ6TdGZLTEw0kszEiRMLvc9y3k\/PPfecqVixoomIiDCDBg0y6enphdZpjDHbt283PXv2NNHR0SYsLMzUr1\/fjBgxwjqx6enTp819991nypUrZ6pWrWomTpyYZ62cJ+k05vyJPAcMGGAqVqxoQkNDTaNGjcz8+fOt6x955BFTsWJFI8l6Xp07d84899xz5sorrzRBQUGmWrVqpmfPnmbLli3W7d5\/\/30THx9vwsLCzO23325ee+21Ip2k8+OPPzYtW7Y0wcHB5uqrrzZLliyxtsnvsc6d33fffWfat29vKlSoYMLCwkyTJk3MZ599doFHBQBQVtFDnUcPVXCdxtBD0UOhLHMYk+M4UABAHt999506duyovXv3qmrVqoVu+8ADD+jUqVOaO3euPckBAACUUvRQAC6EE50DQAEyMjJ09OhRjRs3TnffffcFmykAAADQQwEoOs4pBQAF+OSTT1SzZk2dOnVKEydO9HU6AAAAZQI9FICi4uN7AAAAAAAAsB1HSgEAAAAAAMB2DKUAAAAAAABgO4ZSAAAAAAAAsB1DKQAAAAAAANiOoRQAAAAAAABsx1AKAAAAAAAAtmMoBQAAAAAAANsxlAIAAAAAAIDtGEoBAAAAAADAdgylAAAAAAAAYDuGUgAAAAAAALAdQykAAAAAAADYjqEUAAAAAAAAbMdQCgAAAAAAALZjKAUA\/9OhQwc5HA45HA498MADl7zesmXLrPUcDod27dp1yWsCAADvOH78uCZOnKjOnTsrLi5OoaGhCgkJUbVq1XTjjTdq1KhR+u6772SM8do+T5w4oWeffVbNmjVTZGSkgoODVaVKFTVo0EA9e\/bU+PHjtXfv3gJvv379eo\/ewuFw6IknnvBaflLe\/qUoP1deeaVXc8jPpfZpV155pUfOgYGBKleunKpVq6YWLVpo0KBBWrp0qVdznjFjhsc+AeTFUAqwSVFf4L0xDJFoelB0ue\/jwMBARUREKD4+Xm3atNGwYcO0fv16r+5z3LhxPKYAAJ+ZNm2aatasqdGjR2vRokU6ePCgMjIydO7cOR06dEjfffedXnvtNd144406fPiwV\/a5e\/duNW3aVH\/729+0efNmpaamKjMzU0ePHtVvv\/2muXPnaty4cdqwYUOBa0yfPj1P7KOPPlJWVpZXcrycuFwunT17VocOHdL69ev13nvv6eabb1b79u21b98+X6cHXDYCfZ0AAO\/bvXu32rVrl+cF9ejRox6NT9OmTVW9evV81yio6Xn55ZcVGOif\/3QMHjxYt912mySpUaNGl7xe7dq19eqrr1qXY2JiLnlNO7hcLqWlpSktLU379+\/X6tWrNXnyZN1111167733VKFCBV+nCADARXv11Vf15JNPWpcdDoduuukmXX\/99YqIiNCJEye0efNmrVy5Uunp6V7b7+jRo63eLDAwUHfffbeuvvpqGWO0c+dOrVq1Stu3by\/w9hkZGfr000\/zxA8dOqQFCxZYPcylyt2\/SNK3336rRYsWWZefeeYZj36gfPnyXtm3XWrVqqXBgwcrIyNDSUlJmj9\/vjV8XLFihdq1a6e1a9eqatWqPs4U8H\/++T9LoAzo3bu3mjdvnifujWHI5dz0nD59WpGRkReVT+\/evS\/qdgWpXr26148uK2nNmzdX7969debMGe3YsUPz5s1TcnKyJGn27NnatWuXvvvuO5UrV87HmQIAUHxbt27V008\/bV2uWLGivvzyS7Vp0ybPtqmpqfrnP\/+psLAwj3iHDh20fPlySVL79u21bNmyIu3722+\/tX5\/9tlnNXbs2Hzzy72\/bF9++aVOnDgh6fwgrU6dOtqxY4ek8x8TK6g\/K26++fUvqampHv3ZoEGD8hzpfPjwYb355pv6+uuvlZiYqMzMTMXHx6tLly4aPXq0atSo4bF9Wlqa\/v73v2vu3LnasWOH0tPTVaFCBcXFxalFixbq1auXunbtqnHjxmn8+PEet505c6ZmzpxpXU5KSirWkde5a0xPT9fgwYM1Y8YMSeff4B0+fLhHPzxnzhzNnj1bP\/74ow4fPqyTJ08qODhYNWrU0M0336wnnnjCymHXrl1KSEjIs9+cH+EbO3asxo0bpxMnTujll1\/Whg0blJiYqOPHjysjI0MVKlRQkyZNdP\/99+u+++7j43\/wXwaALZYuXWokWT\/Tp0+\/4G3at29vbd++ffsi76tChQrW7caNG5fvNr\/++qtJSkrK97pZs2ZZt3c4HKZu3brW5V69enk935zGjh3rcT\/lzjHn9TVr1jTHjh0zjz76qLniiiuM0+k0b7zxhjHGmNmzZ5v77rvPNG7c2FSpUsUEBQWZ8PBw06BBAzNkyJB8a8+Zf\/\/+\/a14UlKSR05Lly41n3zyiWnZsqUJCwsz0dHR5k9\/+pPZs2ePx3q5H\/Oc++zfv7\/HfXXgwAEzaNAgExsba4KDg039+vXNtGnT8r2PtmzZYm677TYTGRlpIiMjTdeuXc2mTZvy3DdFlTPHnHUbY8zJkydN165dPbYZPXq0xzbvv\/++ufvuu039+vVNxYoVTWBgoImMjDRNmzY1Tz75pDl69GiB90l+P9l\/Gzt37jTDhw837dq1M\/Hx8aZcuXImODjYxMXFmdtuu818+eWXRa4RAABjjHnkkUc8XnM+\/\/zzYq9xsf1OZGSkdbs+ffqY9PT0Yu23W7du1u3btGlj3nzzTetycHCwOXbsmFfzzelC\/dmqVatMpUqVCnxtL1++vFmxYoXHbTp06FBoP9C7d+98953fT0E9bU41a9Ys9H7IysoyTZs29eiB9+3bZ13fq1evQnOIiooyW7ZsMcbk7R3z+xk7dqwxxpiffvrpgtsOGDCg6A8WUMZwpBTgh3KeV+C3335TRkaGQkJCPLZp0KBBgbfP+dG91q1bq3fv3ho+fLgkad68eTp+\/LgqVqzo5ayLLy0tTe3atdNvv\/2W57qPPvpI\/\/73vz1imZmZ2rp1q7Zu3ap\/\/vOfWrlypRo3blzs\/Y4ZM0YrV660Lp89e1ZffPGFfvzxR23ZskWhoaHFWm\/v3r267rrrdPDgQSv222+\/6eGHH1ZAQIAefPBBK75+\/XrddNNNSk1NtWILFizQsmXLdMMNNxS7lguJjo7W559\/rjp16liHtb\/zzjt6\/vnnFRwcLEl6991385z\/4vTp0\/rxxx\/1448\/6qOPPtIPP\/yguLi4Yu37l19+0ZtvvpknfuDAAR04cEDz58\/X+PHj9dxzz11kdQCAy83ixYut3ytUqKC77rrLtn1fe+211hFLn376qb7++mu1bt1a1157rVq1aqWbb765wKO9Dx486HGkVZ8+fXT33Xdr5MiRcrvdOnfunD7++GP95S9\/saWWnFJSUnTnnXfq2LFjkqSaNWuqd+\/eCgsL0xdffKFffvlFycnJ6tWrl3bs2KHy5ctr69at1hFbTqdT999\/v+rVq6djx44pKSnJ42iuzp07KyIiQlOmTNHOnTsl\/XFkdzZvnCIhICBADzzwgEaOHClJMsZo+fLl+vOf\/yzpfE\/UuXNnNWjQQBUqVFBwcLAOHz6sOXPmaM+ePUpJSdHo0aP19ddfKyYmRq+++qrWr1+vzz77zNpHzk8IZB+d53Q61aBBA7Vs2VKxsbGKjo5Wenq6Nm3apHnz5skYo+nTp+uRRx5Ry5YtL7lOoLRhKAX4yIIFC6wX75x69+5d4Hmeispfm57cjh07pmPHjqlTp05q27atjh49an32vziNQ3GtXLlSLVq0UJcuXbR06VJ9\/\/33kqQdO3Zo7ty56tOnT7HW27lzp0JDQzV48GCFhYVpypQpOnv2rCRp4sSJ1lDKGKMHH3zQYyB17733qlatWpo1a5bHYfXeFBERoT59+lgDotTUVK1fv95qpqpUqaLbb79dtWvXVkxMjAICArR\/\/3599tlnOn78uPbv368XX3xR7777rvWRzZwf06xQoYKeeeYZa38tWrSQdP6jp9dcc42aN2+uypUrKyoqSmlpafr++++tb8d54YUXNHDgQF1xxRUlUjsAwL\/s37\/f+r1u3bpyOv\/43qfffvst3zft+vfvb32s61JMnDhRN9xwg86dOyfp\/DBn4cKFWrhwoSQpNDRUDz\/8sCZMmJDnY\/L\/\/Oc\/5XK5JJ0fntxzzz2qWrWqOnTooCVLlkg6\/xE+X\/RnM2bM0JEjRySdf03fuHGjNSQaNWqUEhISrPOazpw5U8OGDfM4V9dVV12lDz74wOPjaS6XyzoVRZs2bdSmTRvNnz\/fGko1bNiwRE6RcNVVV3lczvl8ee+995SZmak1a9Zox44dSklJUXx8vDp27Gi9obtkyRJlZmYqKipKTzzxhGbMmOExlMov56uvvlq\/\/vqr9uzZo3Xr1unQoUMKCgrSDTfcoA0bNlg5LFy4kKEU\/BJDKcBHPvvsM48XqWzNmze\/5KGUvzY9+RkxYoTeeOONPPHiNA5BQUHF2mfLli21cuVKBQUFWedLyG7G1q1bV+yhlHR+eNijRw9JUo0aNTRixAhJ0rZt26zzZK1du1Y\/\/fSTdZvRo0fr5ZdfliQ9\/vjjql27tk6ePFnsfRdFYU3a119\/rTNnzmj16tXauXOnUlNTlZCQoHbt2uk\/\/\/mPJFnPvexzOOQ8N0V245Zb165d1bVrV23fvl2bNm3S0aNHFRQUpFtvvVVr167VmTNnlJWVpSVLlqhfv34lUjcAwH9d7Dl6inoOqdxatmyptWvXaty4cfr666+VmZnpcX16erreeustJScn5xmC5bzcoUMH6024Pn36WP3Zxo0b9dNPP+U5Cvxi8y2q7DfnJOnkyZOFHk2\/atUqDRs2TA0aNFDFihV1\/Phxbd26VXXq1FGzZs1Ur149NWnSRJ06dVLNmjVLNO\/8GGMKvO6jjz7SiBEj8n1TOVtGRoaOHTumatWqFXmfx48fV\/\/+\/fXVV18Vuh3fCAh\/xVAKKMVoei7s2WefzTdeUo2DJD300EPWICsoKEgJCQnWUOpihkJxcXHWQErKOwA6efKkIiMjtX79eo\/4\/fffb\/1eoUIF9ejRwyvv5OansCbt9ddf19ixYz2O4MrtYhqpXbt2qW\/fvlq1alWh29GkAQCK6oorrrBODr5jxw4ZY6zhVJUqVayPV40dO1Znzpzx+v6vueYazZ07V2fOnNEPP\/ygNWvWaOHChR491MyZM\/X6669bRxutXbtWW7duta7P+eZXr169NGTIEKvXmz59ul5\/\/XWv512Y7JOvF8XRo0clnX+DdNasWRowYID27NmjnTt3WkdBSfr\/7d15fFT19f\/x951shCyEJJClbGETZBEqgoAWFBSVKiBVsFQRqVYLKqBW7beoqC1CXRCh8KU\/RWzBiq1goRVFVq2ICKIVMWAIyiJhCcmQIEmY+fz+yHcumSyQwOROMryej0cej+TMnc89Z+6QHM7cuaPIyEhNnTpVkyZNCni+p1P+g4B8Z2Jv2bJFt912m7xe7xnXKCoqqtE+x44de8aB1NmsC9QXrjNvAqA2zJ8\/X8aYCl\/9+\/cPyPq+picvL09r1qzR1KlTK6y9YMECv0biTE1P2TOKyl53KliSk5MrfTXO1zicbiDlczZ\/4Mt\/ukvZ63VVp1mpyXpl18zLy\/OLp6amnvbnQKqqSVu6dKkeeOCB0w6kJNln7dXE0KFDzziQkmjSAADVN2DAAPv73Nxc\/fOf\/7R\/TkxM1IMPPqgHH3ywyk\/AC5SGDRuqf\/\/+euSRR7RmzRo9+eSTfrf7BmeSKrzgdOedd8qyLFmWpaSkJL8XHxcuXOh3bVEnlL2eU1pamv74xz9W+XXXXXfZ21555ZXKzs7Wpk2b9Oc\/\/1kPP\/ywfX3M4uJiPfTQQ\/rmm28cq8Pj8fg91pZl2b3zm2++afdjlmXp9ddfV0FBgYwx1RooVaWwsFDLly+3fx4wYICysrJ08uRJGWPsSxoAoYyhFBDiQqnpKS8mJqbSeG01Dj7l3+53rh\/RW931EhIS\/H72nZ3lc+DAgXPKoyqFhYV+bzWNi4tTjx49JMkvHhsbq\/fee08\/\/PCDjDGaPXv2We8zMzNTn3\/+uf3zz3\/+c+3du1der1fGGDVp0uSs1wYAnL\/Gjx+vsLAw++e7775bW7durdEa\/fv3t\/ujmryYeO+992rt2rWVnn0cGxvr97Pvb\/6JEyf0t7\/9rdr7OHjwYIXrZZ5tvtXlu8akVHom1NVXX20P93xfDzzwgLp162ZfE+nEiRPavn27XC6XevTooV\/+8pd65plntG7dOjVq1EhS6YtyZXuBsv1SoM9iKyoq0q9+9Su\/\/Y0cOdL+kJYjR47Y8UaNGunmm2+2+9DFixdXuW75Hq983vn5+fZlMyRp8ODBat26tcLCwpSZmakvvvji7IsC6gnevgfUYf3797cvWN6vX79qvz3u3nvv1fDhw9WvX78KA45ANz033HDDOecbaJU1Dr4LmZ6ucajrfIMgn9dff11TpkyRVPoWP9\/1mwLJ7Xbr5z\/\/ud\/Aa\/z48fYn75V9rFu3bq2rrrpKUmkj+fe\/\/73Kdc\/UWJZdV5J+9rOf2WdnrV271j79HwCAmujUqZOeeuop+wM2Dhw4oB49eujaa6\/VxRdfrIiICGVnZ8vtdgd838uWLdOsWbOUnp6ufv36qV27doqMjFRmZqbfizwZGRlq3769JNlnvftceeWVlb4w889\/\/tP+kJT58+f79We17fbbb9fTTz+tw4cP6+TJk+rbt69uuukmtW3bVkVFRcrMzNTatWuVk5OjNWvWKCMjQ3l5ebrwwgvVqVMn9ezZU+np6YqOjtaHH36o\/Px8e+2yL8iV\/VCTf\/3rX3rkkUeUnJys5ORk3X777TXKec+ePXr22WdVXFys7OxsLV++3K\/XycjI8PsE4LKXVsjLy9PgwYPVp08fffjhh34fEFRe+Q9i+fnPf64+ffrI5XLp1ltvVdOmTZWQkGAf46effloHDx7UyZMn9corr3A2OM4LDKWAEBSqTU91nW3jUNddeuml6tKli32x86eeekrZ2dlq0aKFFi9eHJCLnG\/btk3PPvusTpw4oR07dmjZsmV+z4tLLrlEkydPtn++4IIL7AuWf\/HFF7rlllvUsWNHvfPOO\/r444+r3E\/ZJu3QoUMaM2aMLrzwQlmWpXHjxqlt27ZyuVz2GW\/333+\/tm7dqiNHjtSJt44CAOqvRx99VDExMfrNb36joqIieTweLV++3O9tVGWd7sLdZ2P\/\/v16\/fXXK72tQYMG+n\/\/7\/\/ZLyqWPYs9Pj5ey5Ytq\/AhNVLpdSb\/8pe\/SCod2Bw+fFjJyckBzbsqjRo10ttvv60hQ4bo8OHDKigoqPbf6m3btmnbtm2V3tazZ0\/169fP\/vnGG2\/UggULJJW+oDVt2jRJpYPGmg6ldu3apYceeqjS2\/r376+FCxf69cFjxozR888\/r\/3790sq\/RTtFStWSCr9dEZfXuX17t1baWlp+v777yVJb7\/9tv0iou\/arY888ogeeeQRSaVvKfV9iE3nzp2VkZGhzZs316g2oL5hKAWEsFBreqrrbBuH+uCVV17RFVdcYb8d0XcsoqKidOWVV9oXoy\/7Edc18emnn1a4oLrPTTfdpD\/\/+c9+19m4\/\/77tWDBAh07dkyS7LPtwsPDNWrUKC1cuLDSta655ho1bNjQPkuq7PPv9ttvV9OmTXXXXXdp7ty5kkpf0fS99XTAgAH6+uuv\/T4BEACAmrjvvvt00003ad68eXr\/\/feVmZmpo0ePKiIiQk2aNNEFF1ygvn376oYbblD37t0Dss93331X77\/\/vlavXq0dO3bo4MGDys3NVVRUlFq2bKkrrrhCEyZMUNu2bSWVftKt74UfqfTtZJX1ZlJp7+PrCUpKSrRw4ULdf\/\/9kvzf7l\/2rXaB1KdPH23btk2zZs3Sv\/\/9b+3cuVOFhYWKi4tTmzZt1Lt3bw0ZMkQ\/+clPJJV+QMusWbP0n\/\/8R59\/\/rkOHDig\/Px8xcTEqH379hoyZIgmTJig8PBT\/1294YYbNGvWLM2ePVtZWVlndb3KsizLUlRUlBISEtSsWTN169ZNv\/jFL\/wGYT6JiYn68MMP9eCDD+r9999XSUmJOnfurEcffVSNGzeusreMiorSv\/\/9bz388MP6+OOPKz0D7+GHH1ZcXJxefPFFZWdnKykpSddff72eeeYZ3XjjjedUI1AvGACOWLNmjZFkf82fP\/+M9+nXr5+9fb9+\/aq9r6+\/\/trMmjXL3HjjjaZz586madOmJjw83MTExJgLL7zQjBs3zuzcudPefu\/evcblctn7uuuuu6pce\/Xq1X51zJgxw76tY8eOdvzRRx+tdr5lPf74437rZ2dnV3l7y5Ytq1xn165d5sYbbzTx8fEmOjraXHLJJeatt96qcBzKrl\/28R49erQdz87O9rvPmjVr\/PZV1f1Ot6\/Ro0dXeWxPdz9jjPniiy\/M4MGDTWxsrImNjTUDBgwwGzduNL\/61a\/s+3Tv3r3qB7mcsvuSZFwul4mOjjbp6emmd+\/e5t577zWbN2+u8v6fffaZufrqq03Dhg1NbGys6devn1m3bp2ZP3++37rlrVq1yvTt29fExMT4bXfo0CFjjDElJSXmySefNC1btjQRERGmRYsW5qGHHjLHjx83LVu2tLd\/\/PHHq10rAADnk5ycHPvvZUZGhjl+\/HiwUwIAP5Yxp\/mcbwCopoMHDyolJUVS6dsCt23bVuufXHM+Ki4uVnh4eIUzoQoKCtS5c2d9++23kkovUj9v3rxgpAgAAOqIN998UzfffLMk6Z133tE111wT5IwAwB9v3wMQEL4LnEvSn\/70JwZSteSrr77SDTfcoFGjRunCCy9U48aNtXv3bs2dO9ceSLlcLo0bNy7ImQIAgGDz9WcjRoxgIAWgTuJMKQABMX78eM2ePVsjRoyo0af4oWa2bt162mtbREZGas6cObrjjjsczAoAAAAAao6hFADUI0eOHNHvf\/97rV27Vt99953y8\/PVoEEDZWRkqH\/\/\/vr1r3+tDh06BDtNAAAAADgjhlIAAAAAAABw3Nl9ZjgAAAAAAABwDhhKAQAAAAAAwHF8+p4kr9er\/fv3Ky4uTpZlBTsdAABQhxhjdOzYMaWnp8vl4vU8H\/onAABQler2TwylJO3fv1\/NmzcPdhoAAKAO27Nnj5o1axbsNOoM+icAAHAmZ+qfGEpJiouLk1T6YMXHxwd07V27dumRcbfrmZ82VesmsYFd+1CBHll+UM\/MflWtW7cO6NoAAKCU2+1W8+bN7X4BpWqzfwIAAPVbdfsnhlKSfcp5fHx8wJuquLg4RYSHKa5BhOIbRgR27QYRpWvHxdEMAgBQy3iLmr\/a7J8AAEBoOFP\/xIURAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOMYSgEAAAAAAMBxDKUAAAAAAADgOIZSAAAAAAAAcBxDKQAAAAAAADiOoRQAAAAAAAAcF9Sh1Pr163X99dcrPT1dlmVp6dKlVW579913y7IszZgxwy+em5urUaNGKT4+XgkJCRo7dqwKCgpqN3EAAIAgoocCAAChIKhDqcLCQl100UWaPXv2abdbsmSJPv74Y6Wnp1e4bdSoUdq2bZtWrlyp5cuXa\/369brrrrtqK2UAAICgo4cCAAChIDyYO7\/22mt17bXXnnabffv26d5779W7776rwYMH+922fft2rVixQps2bVKPHj0kSS+99JKuu+46Pfvss5U2YAAAAPUdPRQAAAgFQR1KnYnX69Wtt96qhx56SJ06dapw+4YNG5SQkGA3U5I0cOBAuVwubdy4UcOGDat03aKiIhUVFdk\/u91uSZLH45HH45EkWZYll8slr9crY4y9bVVxl8sly7IqxH3fe+WSp8yJaS557XhZVcXD5JUpF\/d9b4yx8z6b3Gtaky9edp++uFR63KoTDwsLkzHGL+7Lpao4NVETNVETNVGT0zWVX68+qI0eysn+iecnNVETNVETNVFT\/a6puv1TnR5KTZs2TeHh4brvvvsqvf3AgQNq2rSpXyw8PFyJiYk6cOBAletOnTpVU6ZMqRDPyspSbGysJKlRo0ZKS0tTTk6O8vPz7W2Sk5OVnJysffv2qbCw0I6npqYqISFBu3fvVnFxsR33HZAjCV3liYi24xklOxSuEu2M8G8U25Vs00lFKDuivR1zyaP2JV+p0IrV3vAMO+6Oz5e0XydOnNDOnTvteExMjJo3b67c3FwdPnzYjgeqpmbNmik2NlZZWVl+T8SMjAyFh4f75SJJ7dq108mTJ5WdnX2qJpdL7du3V2Fhofbu3WvHIyMj1bp1a+Xn5\/sdQ2qiJmqiJmqipmDVVB+vs1QbPZST\/RPPT2qiJmqiJmqipvpdU3X7J8uUHZEFkWVZWrJkiYYOHSpJ2rx5swYPHqwtW7bYp5C3atVKEyZM0IQJEyRJf\/jDH7RgwQJlZmb6rdW0aVNNmTJF99xzT6X7quyVPt9Bjo+Pt\/MJxNQxOztbE8eO0PND09U6JfbU9gE4U2pXToEmLd2vF15+QxkZp4ZV9XWSWjaXUJkOUxM1URM1UVP9r8ntdisxMVH5+fl2n1CXONVDOdk\/8fykJmqiJmqiJmqq3zVVt3+qs2dKffDBBzp48KBatGhhxzwejx544AHNmDFDu3fvVmpqqg4ePOh3v5MnTyo3N1epqalVrh0VFaWoqKgK8bCwMIWFhfnFfA94edWNW5ZVGpdXYfJW2L6yWFVxq1zcN8CyLKtC3oHI\/UzxyvZZ03hVuVMTNZ0uTk3URE3UdLp4oGuq6n51VW31UE72T2XXPtd4qD8\/qxOnJmqqKseaxqmJms4mTk3nZ03V7Z\/q7FDq1ltv1cCBA\/1igwYN0q233qoxY8ZIknr37q28vDxt3rxZF198sSRp9erV8nq96tWrl+M5AwAABBs9FAAAqC+COpQqKCjQN998Y\/+cnZ2trVu3KjExUS1atFBSUpLf9hEREUpNTdUFF1wgSerYsaOuueYa3XnnnZo7d65KSko0fvx4jRw5kk+NAQAAIYseCgAAhILKz9tyyKeffqru3bure\/fukqRJkyape\/fueuyxx6q9xsKFC9WhQwcNGDBA1113nS677DLNmzevtlIGAAAIOnooAAAQCoJ6plT\/\/v39LrB1Jrt3764QS0xM1KJFiwKYFQAAQN1GDwUAAEJBUM+UAgAAAAAAwPmJoRQAAAAAAAAcx1AKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOMYSgEAAAAAAMBxDKUAAAAAAADgOIZSAAAAAAAAcBxDKQAAAAAAADiOoRQAAAAAAAAcx1AKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxwV1KLV+\/Xpdf\/31Sk9Pl2VZWrp0qX1bSUmJHn74YXXp0kUxMTFKT0\/Xbbfdpv379\/utkZubq1GjRik+Pl4JCQkaO3asCgoKHK4EAADAOfRQAAAgFAR1KFVYWKiLLrpIs2fPrnDb8ePHtWXLFk2ePFlbtmzRW2+9pczMTN1www1+240aNUrbtm3TypUrtXz5cq1fv1533XWXUyUAAAA4jh4KAACEgvBg7vzaa6\/VtddeW+ltjRo10sqVK\/1is2bNUs+ePfXdd9+pRYsW2r59u1asWKFNmzapR48ekqSXXnpJ1113nZ599lmlp6fXeg0AAABOo4cCAAChIKhDqZrKz8+XZVlKSEiQJG3YsEEJCQl2MyVJAwcOlMvl0saNGzVs2LBK1ykqKlJRUZH9s9vtliR5PB55PB5JkmVZcrlc8nq9MsbY21YVd7lcsiyrQtz3vVcuecqcmOaS146XVVU8TF6ZcnHf98YYO++zyb2mNfniZffpi0uS1+utVjwsLEzGGL+4L5eq4tRETdRETdRETU7XVH69+igQPZST\/RPPT2qiJmqiJmqipvpdU3X7p3ozlDpx4oQefvhh3XLLLYqPj5ckHThwQE2bNvXbLjw8XImJiTpw4ECVa02dOlVTpkypEM\/KylJsbKyk0lcZ09LSlJOTo\/z8fHub5ORkJScna9++fSosLLTjqampSkhI0O7du1VcXGzHfQfkSEJXeSKi7XhGyQ6Fq0Q7Izr55dCuZJtOKkLZEe3tmEsetS\/5SoVWrPaGZ9hxd3y+pP06ceKEdu7cacdjYmLUvHlz5ebm6vDhw3Y8UDU1a9ZMsbGxysrK8nsiZmRkKDw83C8XSWrXrp1Onjyp7OzsUzW5XGrfvr0KCwu1d+9eOx4ZGanWrVsrPz\/f7xhSEzVREzVREzUFq6b6fp2lQPVQTvZPPD+piZqoiZqoiZrqd03V7Z8sU3ZEFkSWZWnJkiUaOnRohdtKSko0fPhw7d27V2vXrrUbqj\/84Q9asGCBMjMz\/bZv2rSppkyZonvuuafSfVX2Sp\/vIPvWDtTUMTs7WxPHjtDzQ9PVOiX21PYBOFNqV06BJi3drxdefkMZGaeGVfV1klo2l1CZDlMTNVETNVFT\/a\/J7XYrMTFR+fn5dp9QlzjVQznZP\/H8pCZqoiZqoiZqqt81Vbd\/qvNnSpWUlOjmm2\/Wt99+q9WrV\/sVk5qaqoMHD\/ptf\/LkSeXm5io1NbXKNaOiohQVFVUhHhYWprCwML+Y7wEvr7pxy7JK4\/IqTN4K21cWqypulYv7BliWZVXIOxC5nyle2T5rGq8qd2qiptPFqYmaqImaThcPdE1V3a+uC3QP5WT\/VHbtc42H+vOzOnFqoqaqcqxpnJqo6Wzi1HR+1lTd\/qnybOoIXzO1c+dOvf\/++0pKSvK7vXfv3srLy9PmzZvt2OrVq+X1etWrVy+n0wUAAKgT6KEAAEB9ENQzpQoKCvTNN9\/YP2dnZ2vr1q1KTExUWlqafvazn2nLli1avny5PB6P\/b7KxMRERUZGqmPHjrrmmmt05513au7cuSopKdH48eM1cuRIPjUGAACELHooAAAQCoI6lPr00091xRVX2D9PmjRJkjR69Gg98cQT+uc\/\/ylJ6tatm9\/91qxZo\/79+0uSFi5cqPHjx2vAgAFyuVwaPny4Zs6c6Uj+AAAAwUAPBQAAQkFQh1L9+\/f3u8BWedW5BntiYqIWLVoUyLQAAADqNHooAAAQCur0NaUAAAAAAAAQmhhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOMYSgEAAAAAAMBxDKUAAAAAAADgOIZSAAAAAAAAcBxDKQAAAAAAADiOoRQAAAAAAAAcx1AKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHBce7ARQOw4dOiS32x3wdePj49WkSZOArwsAAAAAAM4vDKVC0KFDh3TPmFEqOnYk4GtHxSVpzvyFDKYAAAAAAMA5YSgVgtxut4qOHdEDl8ereVLDgK2758hxPffBEbndboZSAAAAAADgnDCUCmHNkxqqTUpsgFcN\/FsCAQAAAADA+YcLnQMAAAAAAMBxDKUAAAAAAADgOIZSAAAAAAAAcBxDKQAAAAAAADiOoRQAAAAAAAAcx1AKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHFBHUqtX79e119\/vdLT02VZlpYuXep3uzFGjz32mNLS0hQdHa2BAwdq586dftvk5uZq1KhRio+PV0JCgsaOHauCggIHqwAAAHAWPRQAAAgFQR1KFRYW6qKLLtLs2bMrvX369OmaOXOm5s6dq40bNyomJkaDBg3SiRMn7G1GjRqlbdu2aeXKlVq+fLnWr1+vu+66y6kSAAAAHEcPBQAAQkF4MHd+7bXX6tprr630NmOMZsyYod\/97ncaMmSIJOm1115TSkqKli5dqpEjR2r79u1asWKFNm3apB49ekiSXnrpJV133XV69tlnlZ6e7lgtAAAATqGHAgAAoaDOXlMqOztbBw4c0MCBA+1Yo0aN1KtXL23YsEGStGHDBiUkJNjNlCQNHDhQLpdLGzdudDxnAACAYKOHAgAA9UVQz5Q6nQMHDkiSUlJS\/OIpKSn2bQcOHFDTpk39bg8PD1diYqK9TWWKiopUVFRk\/+x2uyVJHo9HHo9HkmRZllwul7xer4wx9rZVxV0ulyzLqhD3fe+VS54yM0CXvHa8rKriYfLKlIv7vjfG2HlLktdbuoaR5bdPS0YuGXllyciqJO7Sqcwll4ysMnGvXHKFhdk1ld2n7zEou\/8zxcP+b62ycd\/jW1W8usejpsfJF6cmaqImaqImaipfU\/n16rra6qGc7J94flITNVETNVETNdXvmqrbP9XZoVRtmjp1qqZMmVIhnpWVpdjYWEmlryimpaUpJydH+fn59jbJyclKTk7Wvn37VFhYaMdTU1OVkJCg3bt3q7i42I77DsiRhK7yRETb8YySHQpXiXZGdPLLoV3JNp1UhLIj2tsxlzxqX\/KVCq1Y7Q3PsOPu+HxJ+3XixAm\/i5f6LlJa2CBVOyNa2fFG3lylefYpJyxd+a7EUzV5cpTsPah94S1UaMWdqsmzVwneo9od3kbFVgPlNi5Wt54Fdn1ZWVl+T8SMjAyFh4dXuJBqu3btdPLkSWVnZ5+qyeVS+\/btVVhYqL1799rxyMhItW7dWvn5+X5NcUxMjJo3b67c3FwdPnz4VE0BOk7NmjVTbGwsNVETNVETNVFThZq4+HcpJ\/snnp\/URE3URE3URE31u6bq9k+WKTsiCyLLsrRkyRINHTpUkrRr1y61adNGn332mbp162Zv169fP3Xr1k0vvviiXnnlFT3wwAM6evSoffvJkyfVoEEDvfnmmxo2bFil+6rslT7fQY6Pj7fzCcTUMTs7WxPHjtDzQ9PVOiX21PYBOFNqV06BJi3drxdefkMZGaeGVbt27dKkX47UC0PTlJFyash0rmdK7cop0IPLcvTcvEVq27Yt02FqoiZqoiZqOi9qcrvdSkxMVH5+vt0n1CVO9VBO9k88P6mJmqiJmqiJmup3TdXtn+rsmVIZGRlKTU3VqlWr7IbK7XZr48aNuueeeyRJvXv3Vl5enjZv3qyLL75YkrR69Wp5vV716tWryrWjoqIUFRVVIR4WFqawsDC\/mO8BL6+6ccsqHf645FWYvBW2ryxWVdwqF\/cNsCzL8svbl4MlU+k6pSOmirNIVxW5+OIueeX1eOyayj9Wdu41iJfP\/Uzxcz0eZ4pTEzVREzWdLk5N52dNVd2vrqqtHsrJ\/qns2ucaD\/XnZ3Xi1ERNVeVY0zg1UdPZxKnp\/Kypuv1TUIdSBQUF+uabb+yfs7OztXXrViUmJqpFixaaMGGCnn76abVr104ZGRmaPHmy0tPT7VcCO3bsqGuuuUZ33nmn5s6dq5KSEo0fP14jR47kU2MAAEDIoocCAAChIKhDqU8\/\/VRXXHGF\/fOkSZMkSaNHj9arr76q3\/zmNyosLNRdd92lvLw8XXbZZVqxYoUaNGhg32fhwoUaP368BgwYIJfLpeHDh2vmzJmO1wIAAOAUeigAABAKgjqU6t+\/v997GcuzLEtPPvmknnzyySq3SUxM1KJFi2ojPQAAgDqJHgoAAISCyt9MCAAAAAAAANQihlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOMYSgEAAAAAAMBxNR5K\/fDDDzp+\/Lj987fffqsZM2bovffeC2hiAAAAoYQeCgAAwF+Nh1JDhgzRa6+9JknKy8tTr1699Nxzz2nIkCGaM2dOwBMEAAAIBfRQAAAA\/mo8lNqyZYsuv\/xySdLf\/\/53paSk6Ntvv9Vrr72mmTNnBjxBAACAUEAPBQAA4K\/GQ6njx48rLi5OkvTee+\/pxhtvlMvl0qWXXqpvv\/024AkCAACEAnooAAAAfzUeSrVt21ZLly7Vnj179O677+rqq6+WJB08eFDx8fEBTxAAACAU0EMBAAD4q\/FQ6rHHHtODDz6oVq1aqWfPnurdu7ek0lf8unfvHvAEAQAAQgE9FAAAgL\/wmt7hZz\/7mS677DJ9\/\/33uuiii+z4gAEDNGzYsIAmBwAAECrooQAAAPzV+EwpSUpNTVVcXJxWrlypH374QZJ0ySWXqEOHDgFNDgAAIJTQQwEAAJxS46HUkSNHNGDAALVv317XXXedvv\/+e0nS2LFj9cADDwQ8QQAAgFBADwUAAOCvxkOpiRMnKiIiQt99950aNmxox0eMGKEVK1YENDkAAIBQQQ8FAADgr8bXlHrvvff07rvvqlmzZn7xdu3a8XHGAAAAVaCHAgAA8FfjM6UKCwv9Xt3zyc3NVVRUVECSAgAACDX0UAAAAP5qPJS6\/PLL9dprr9k\/W5Ylr9er6dOn64orrghocgAAAKGCHgoAAMBfjd++N336dA0YMECffvqpiouL9Zvf\/Ebbtm1Tbm6u\/vOf\/9RGjgAAAPUePRQAAIC\/Gp8p1blzZ+3YsUOXXXaZhgwZosLCQt1444367LPP1KZNm9rIEQAAoN6jhwIAAPBX4zOlJKlRo0b6n\/\/5n0DnAgAAENLooQAAAE6p8ZlS8+fP15tvvlkh\/uabb2rBggUBSQoAACDU0EMBAAD4q\/FQaurUqUpOTq4Qb9q0qf7whz8EJCkAAIBQQw8FAADgr8ZDqe+++04ZGRkV4i1bttR3330XkKQAAABCDT0UAACAvxoPpZo2baovvviiQvzzzz9XUlJSQJICAAAINfRQAAAA\/mo8lLrlllt03333ac2aNfJ4PPJ4PFq9erXuv\/9+jRw5sjZyBAAAqPfooQAAAPzV+NP3nnrqKe3evVsDBgxQeHjp3b1er2677TauhwAAAFAFeigAAAB\/NR5KRUZG6o033tBTTz2lzz\/\/XNHR0erSpYtatmxZG\/kBAACEBHooAAAAfzUeSvm0b99e7du3D2QuAAAAIY8eCgAAoFSNh1Iej0evvvqqVq1apYMHD8rr9frdvnr16oAlBwAAECrooQAAAPzVeCh1\/\/3369VXX9XgwYPVuXNnWZZVG3kBAACEFHooAAAAfzUeSv3tb3\/T4sWLdd1119VGPgAAACGJHgoAAMCfq6Z3iIyMVNu2bWsjFwAAgJBFDwUAAOCvxkOpBx54QC+++KKMMbWRDwAAQEiihwIAAPBX47fvffjhh1qzZo3eeecdderUSREREX63v\/XWWwFLDgAAIFTQQwEAAPir8VAqISFBw4YNq41cAAAAQhY9FAAAgL8aD6Xmz59fG3kAAACENHooAAAAfzW+phQAAAAAAABwrmp8ppQk\/f3vf9fixYv13Xffqbi42O+2LVu2BCQxAACAUEMPBQAAcEqNz5SaOXOmxowZo5SUFH322Wfq2bOnkpKStGvXLl177bW1kSMAAEC9Rw8FAADgr8ZDqT\/96U+aN2+eXnrpJUVGRuo3v\/mNVq5cqfvuu0\/5+fm1kSMAAEC9Rw8FAADgr8ZDqe+++059+vSRJEVHR+vYsWOSpFtvvVWvv\/56QJPzeDyaPHmyMjIyFB0drTZt2uipp56SMcbexhijxx57TGlpaYqOjtbAgQO1c+fOgOYBAABwruihAAAA\/NV4KJWamqrc3FxJUosWLfTxxx9LkrKzs\/0anUCYNm2a5syZo1mzZmn79u2aNm2apk+frpdeesneZvr06Zo5c6bmzp2rjRs3KiYmRoMGDdKJEycCmgsAAMC5oIcCAADwV+Oh1JVXXql\/\/vOfkqQxY8Zo4sSJuuqqqzRixAgNGzYsoMl99NFHGjJkiAYPHqxWrVrpZz\/7ma6++mp98sknkkpf4ZsxY4Z+97vfaciQIeratatee+017d+\/X0uXLg1oLgAAAOeCHgoAAMBfjT99b968efJ6vZKkcePGKSkpSR999JFuuOEG\/epXvwpocn369NG8efO0Y8cOtW\/fXp9\/\/rk+\/PBDPf\/885JKX1k8cOCABg4caN+nUaNG6tWrlzZs2KCRI0cGNB8AAICzRQ8FAADgr8ZDqb1796p58+b2zyNHjtTIkSNljNGePXvUokWLgCX3yCOPyO12q0OHDgoLC5PH49Hvf\/97jRo1SpJ04MABSVJKSorf\/VJSUuzbKlNUVKSioiL7Z7fbLan0+gsej0eSZFmWXC6XvF6v3yn1VcVdLpcsy6oQ933vlUueMiemueS142VVFQ+TV6Zc3Pe9McbOW5Ld8BpZfvu0ZOSSkVeWjKxK4i6VffOAS0ZWmbhXLrnCwuyayu7T9xiU3f+Z4mH\/t1bZuO\/xrSpe3eNR0+Pki1MTNVETNVETNZWvqfx6Z6u+91BO9k88P6mJmqiJmqiJmup3TdXtn2o8lMrIyND333+vpk2b+sVzc3OVkZERsMZNkhYvXqyFCxdq0aJF6tSpk7Zu3aoJEyYoPT1do0ePPut1p06dqilTplSIZ2VlKTY2VlLpq4VpaWnKycnx+0Sc5ORkJScna9++fSosLLTjqampSkhI0O7du1VcXGzHfQfkSEJXeSKi7XhGyQ6Fq0Q7Izr55dCuZJtOKkLZEe3tmEsetS\/5SoVWrPaGZ9hxd3y+pP06ceKE34VJCwoKJEmFDVK1M6KVHW\/kzVWaZ59ywtKV70o8VZMnR8neg9oX3kKFVtypmjx7leA9qt3hbVRsNVBu42J161lg15eVleX3RMzIyFB4eHiFi6S2a9dOJ0+eVHZ29qmaXC61b99ehYWF2rt3rx2PjIxU69atlZ+f79cUx8TEqHnz5srNzdXhw4dP1RSg49SsWTPFxsZSEzVREzVREzVVqMn3d\/Vc1fceysn+iecnNVETNVETNVFT\/a6puv2TZWp4ZU2Xy6WcnBw1adLEL\/7tt9\/qwgsv9Cv6XDVv3lyPPPKIxo0bZ8eefvpp\/fWvf9XXX3+tXbt2qU2bNvrss8\/UrVs3e5t+\/fqpW7duevHFFytdt7JX+nwHOT4+XlLgpo7Z2dmaOHaEnh+artYpsae2D8CZUrtyCjRp6X698PIbysg4NazatWuXJv1ypF4YmqaMlFNDpnM9U2pXToEeXJaj5+YtUtu2bZkOUxM1URM1UdN5UZPb7VZiYqLy8\/PtPuFs1Pceysn+iecnNVETNVETNVFT\/a6puv1Ttc+UmjRpkl3g5MmT1bBhQ\/s2j8ejjRs3+jU1gXD8+HG7YJ+wsDC7yIyMDKWmpmrVqlX2vt1utzZu3Kh77rmnynWjoqIUFRVVIR4WFqawsDC\/WPn91zRuWaXDH5e8CpO3wvaVxaqKW+XivgGWZVl+eftysGQqXad0xFRxFumqIhdf3CWvvB6PXVP5x8rOvQbx8rmfKX6ux+NMcWqiJmqiptPFqen8rKmq+1VXqPRQTvZPZdc+13ioPz+rE6cmaqoqx5rGqYmaziZOTednTdXtn6o9lPrss88klV6\/6L\/\/\/a8iIyPt2yIjI3XRRRfpwQcfrO5y1XL99dfr97\/\/vVq0aKFOnTrps88+0\/PPP6877rhDUmnBEyZM0NNPP6127dopIyNDkydPVnp6uoYOHRrQXAAAAM4GPRQAAEDlqj2UWrNmjaTSjzB+8cUXz+n09ep66aWXNHnyZP3617\/WwYMHlZ6erl\/96ld67LHH7G1+85vfqLCwUHfddZfy8vJ02WWXacWKFWrQoEGt5wcAAHAm9FAAAACVq\/E1pcpzu91avXq1OnTooA4dOgQqL0e53W41atTonK8VUZmsrCxNuONmzRiaqjZlrikVkLVzCjRh6QHNeGWx2rRpU+v7rGp\/AACEstrqE+p7D1Wb\/RMAAKjfqtsnVP5mwtO4+eabNWvWLEnSDz\/8oB49eujmm29Wly5d9I9\/\/OPsMwYAAAhh9FAAAAD+ajyUWr9+vS6\/\/HJJ0pIlS2SMUV5enmbOnKmnn3464AkCAACEAnooAAAAfzUeSuXn5ysxMVGStGLFCg0fPlwNGzbU4MGDtXPnzoAnCAAAEArooQAAAPzVeCjVvHlzbdiwQYWFhVqxYoWuvvpqSdLRo0e5MCYAAEAV6KEAAAD8VfvT93wmTJigUaNGKTY2Vi1btlT\/\/v0llZ6S3qVLl0DnBwAAEBLooQAAAPzVeCj161\/\/Wj179tSePXt01VVXyeUqPdmqdevWXA8BAACgCvRQAAAA\/mo8lJKkHj16qEePHn6xwYMHByQhAACAUEUPBQAAcEqNh1Iej0evvvqqVq1apYMHD8rr9frdvnr16oAlBwAAECrooQAAAPzVeCh1\/\/3369VXX9XgwYPVuXNnWZZVG3kBAACEFHooAAAAfzUeSv3tb3\/T4sWLdd1119VGPgAAACGJHgoAAMCfq6Z3iIyMVNu2bWsjFwAAgJBFDwUAAOCvxkOpBx54QC+++KKMMbWRDwAAQEiihwIAAPBX47fvffjhh1qzZo3eeecdderUSREREX63v\/XWWwFLDgAAIFTQQwEAAPir8VAqISFBw4YNq41cAAAAQhY9FAAAgL8aD6Xmz59fG3kAAACENHooAAAAfzW+phQAAAAAAABwrqp1ptSPf\/xjrVq1So0bN1b37t1lWVaV227ZsiVgyQEAANRn9FAAAABVq9ZQasiQIYqKipIkDR06tDbzAQAACBn0UAAAAFWr1lDq8ccfr\/R7AAAAVI0eCgAAoGpcUwoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOOqNZRyu921nQcAAEDIoYcCAACoWrWGUo0bN9bBgwclSVdeeaXy8vJqMycAAICQQA8FAABQtWoNpWJjY3XkyBFJ0tq1a1VSUlKrSQEAAIQCeigAAICqhVdno4EDB+qKK65Qx44dJUnDhg1TZGRkpduuXr06cNkBAADUY\/RQAAAAVavWUOqvf\/2rFixYoKysLK1bt06dOnVSw4YNazs3AACAeo0eCgAAoGrVGkpFR0fr7rvvliR9+umnmjZtmhISEmozLwAAgHqPHgoAAKBq1RpKlbVmzRr7e2OMJMmyrMBlBAAAEILooQAAAPxV60Ln5b322mvq0qWLoqOjFR0dra5du+ovf\/lLoHMDAAAIKfRQAAAAp9T4TKnnn39ekydP1vjx49W3b19J0ocffqi7775bhw8f1sSJEwOeJAAAQH1HDwUAAOCvxkOpl156SXPmzNFtt91mx2644QZ16tRJTzzxBA0VAABAJeihau7QoUNyu90BXzc+Pl5NmjQJ+LoAAKBmajyU+v7779WnT58K8T59+uj7778PSFIAAAChhh6qZg4dOqR7xoxS0bEjAV87Ki5Jc+YvZDAFAECQ1Xgo1bZtWy1evFi\/\/e1v\/eJvvPGG2rVrF7DEAAAAQgk9VM243W4VHTuiBy6PV\/OkhgFbd8+R43rugyNyu90MpQAACLIaD6WmTJmiESNGaP369fb1EP7zn\/9o1apVWrx4ccATBAAACAX0UGeneVJDtUmJDfCqgX9LIAAAqLkaf\/re8OHDtXHjRiUnJ2vp0qVaunSpkpOT9cknn2jYsGG1kSMAAEC9Rw8FAADgr8ZnSknSxRdfrL\/+9a+BzgUAACCk0UMBAACcUuMzpQAAAAAAAIBzxVAKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQEbSv3pT3\/Sk08+GajlAAAAzgv0UAAA4HwVsKHUP\/7xD7366quBWg4AAOC8QA8FAADOVwEbSq1atUq7du0K1HK2ffv26Re\/+IWSkpIUHR2tLl266NNPP7VvN8boscceU1pamqKjozVw4EDt3Lkz4HkAAADUBnooAABwvjqnoZQxRsaYQOVSwdGjR9W3b19FRETonXfe0VdffaXnnntOjRs3treZPn26Zs6cqblz52rjxo2KiYnRoEGDdOLEiVrLCwAA4FzQQwEAAJzlUOq1115Tly5dFB0drejoaHXt2lV\/+ctfAp2bpk2bpubNm2v+\/Pnq2bOnMjIydPXVV6tNmzaSShu6GTNm6He\/+52GDBmirl276rXXXtP+\/fu1dOnSgOcDAABwLuihAAAATgmv6R2ef\/55TZ48WePHj1ffvn0lSR9++KHuvvtuHT58WBMnTgxYcv\/85z81aNAg3XTTTVq3bp1+9KMf6de\/\/rXuvPNOSVJ2drYOHDiggQMH2vdp1KiRevXqpQ0bNmjkyJGVrltUVKSioiL7Z7fbLUnyeDzyeDySJMuy5HK55PV6\/V7JrCrucrlkWVaFuO97r1zylJkBuuS142VVFQ+TV6Zc3Pe9McbOW5K83tI1jCy\/fVoycsnIK0tGViVxl8q+ZuuSkVUm7pVLrrAwu6ay+\/Q9BmX3f6Z42P+tVTbue3yrilf3eNT0OPni1ERN1ERN1ERN5Wsqv97Zqu89lJP9k+\/YuMLC\/Hqo2uyf6uvzs2wuofJvjpqoiZqoiZrqf03V7Z9qPJR66aWXNGfOHN1222127IYbblCnTp30xBNPBLSh2rVrl+bMmaNJkybpt7\/9rTZt2qT77rtPkZGRGj16tA4cOCBJSklJ8btfSkqKfVtlpk6dqilTplSIZ2VlKTY2VlJpY5aWlqacnBzl5+fb2yQnJys5OVn79u1TYWGhHU9NTVVCQoJ2796t4uJiO+47IEcSusoTEW3HM0p2KFwl2hnRyS+HdiXbdFIRyo5ob8dc8qh9yVcqtGK1NzzDjrvj8yXt14kTJ\/yuAVFQUCBJKmyQqp0Rrex4I2+u0jz7lBOWrnxX4qmaPDlK9h7UvvAWKrTiTtXk2asE71HtDm+jYquBchsXq1vPAru+rKwsvydiRkaGwsPDK1yPol27djp58qSys7NP1eRyqX379iosLNTevXvteGRkpFq3bq38\/Hy\/YxgTE6PmzZsrNzdXhw8fPlVTgI5Ts2bNFBsbS03URE3URE3UVKEm39\/Vc1Xfeygn+6dmzZpJkrr8+FIdapwgT0SkpNrtn+rr81MKvX9z1ERN1ERN1FT\/a6pu\/2SZGl7QoEGDBvryyy\/Vtm1bv\/jOnTvVpUuXgF6HIDIyUj169NBHH31kx+677z5t2rRJGzZs0EcffaS+fftq\/\/79SktLs7e5+eabZVmW3njjjUrXreyVPt9Bjo+PlxS4qWN2drYmjh2h54emq3VK7KntA\/BK366cAk1aul8vvPyGMjJONVu7du3SpF+O1AtD05SRcmrIdK5nSu3KKdCDy3L03LxFatu2LdNhaqImaqImajovanK73UpMTFR+fr7dJ5yN+t5DOdk\/uVyu0n7mzlv07PUpdg9Vm\/1TfX1+ls0lVP7NURM1URM1UVP9r6m6\/VONz5Rq27atFi9erN\/+9rd+8TfeeEPt2rWr6XKnlZaWpgsvvNAv1rFjR\/3jH\/+QVDrpk6ScnBy\/hionJ0fdunWrct2oqChFRUVViIeFhSksLMwv5nvAy6tu3LJKhz8ueRUmb4XtK4tVFbfKxX0NmGVZfnn7crBkKl2ndMRUcRbpqiIXX9wlr7wej11T+cfKzr0G8fK5nyl+rsfjTHFqoiZqoqbTxanp\/KypqvvVVH3voZzsn3y8Hk+lPVRt9E+Bzp1\/c9RETdR0NnFqoqZQqam6\/VONh1JTpkzRiBEjtH79evt6CP\/5z3+0atUqLV68uKbLnVbfvn2VmZnpF9uxY4datmwpqfR0stTUVK1atcpuoNxutzZu3Kh77rknoLkAAACcC3ooAAAAfzUeSg0fPlwbN27UCy+8YH86S8eOHfXJJ5+oe\/fuAU1u4sSJ6tOnj\/7whz\/o5ptv1ieffKJ58+Zp3rx5kkqncBMmTNDTTz+tdu3aKSMjQ5MnT1Z6erqGDh0a0FwAAADOBT0UAACAvxoPpSTp4osv1l\/\/+tdA51LBJZdcoiVLlujRRx\/Vk08+qYyMDM2YMUOjRo2yt\/nNb36jwsJC3XXXXcrLy9Nll12mFStWqEGDBrWeHwAAQE3QQwEAAJxyVkMpJ\/30pz\/VT3\/60ypvtyxLTz75pJ588kkHswIAAKjb6KEAAEBdV+2hlO+K7KdjWZZOnjx5zkkBAACECnooAACAylV7KLVkyZIqb9uwYYNmzpxZ4SMBAQAAznf0UAAAAJWr9lBqyJAhFWKZmZl65JFHtGzZMo0aNYrTvwEAAMqhhwIAAKic62zutH\/\/ft15553q0qWLTp48qa1bt2rBggX2xwwDAACgInooAACAU2o0lMrPz9fDDz+stm3batu2bVq1apWWLVumzp0711Z+AAAA9R49FAAAQEXVfvve9OnTNW3aNKWmpur111+v9FR0AAAA+KOHAgAAqFy1h1KPPPKIoqOj1bZtWy1YsEALFiyodLu33norYMkBAADUd\/RQAAAAlav2UOq2224748cZAwAAwB89FAAAQOWqPZR69dVXazENAACA0EQPBQAAULmz+vQ9AAAAAAAA4FwwlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOMYSgEAAAAAAMBxDKUAAAAAAADgOIZSAAAAAAAAcBxDKQAAAAAAADiOoRQAAAAAAAAcx1AKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHH1aij1zDPPyLIsTZgwwY6dOHFC48aNU1JSkmJjYzV8+HDl5OQEL0kAAIA6hh4KAADURfVmKLVp0yb97\/\/+r7p27eoXnzhxopYtW6Y333xT69at0\/79+3XjjTcGKUsAAIC6hR4KAADUVfViKFVQUKBRo0bpz3\/+sxo3bmzH8\/Pz9fLLL+v555\/XlVdeqYsvvljz58\/XRx99pI8\/\/jiIGQMAAAQfPRQAAKjLwoOdQHWMGzdOgwcP1sCBA\/X000\/b8c2bN6ukpEQDBw60Yx06dFCLFi20YcMGXXrppZWuV1RUpKKiIvtnt9stSfJ4PPJ4PJIky7Lkcrnk9XpljLG3rSrucrlkWVaFuO97r1zylJkBuuS142VVFQ+TV6Zc3Pe9McbOW5K83tI1jCy\/fVoycsnIK0tGViVxl05lLrlkZJWJe+WSKyzMrqnsPn2PQdn9nyke9n9rlY37Ht+q4tU9HjU9Tr44NVETNVETNVFT+ZrKr1efBLKHcrJ\/8h0bV1iYXw9Vm\/1TfX1+ls0lVP7NURM1URM1UVP9r6m6\/VOdH0r97W9\/05YtW7Rp06YKtx04cECRkZFKSEjwi6ekpOjAgQNVrjl16lRNmTKlQjwrK0uxsbGSpEaNGiktLU05OTnKz8+3t0lOTlZycrL27dunwsJCO56amqqEhATt3r1bxcXFdtx3QI4kdJUnItqOZ5TsULhKtDOik18O7Uq26aQilB3R3o655FH7kq9UaMVqb3iGHXfH50varxMnTmjnzp12vKCgQJJU2CBVOyNa2fFG3lylefYpJyxd+a7EUzV5cpTsPah94S1UaMWdqsmzVwneo9od3kbFVgPlNi5Wt54Fdn1ZWVl+T8SMjAyFh4f75SJJ7dq108mTJ5WdnX2qJpdL7du3V2Fhofbu3WvHIyMj1bp1a+Xn5\/sdw5iYGDVv3ly5ubk6fPjwqZoCdJyaNWum2NhYaqImaqImaqKmCjX5\/q7WN4HuoZzsn5o1ayZJ6vLjS3WocYI8EZGSard\/qq\/PTyn0\/s1REzVREzVRU\/2vqbr9k2XKjsjqmD179qhHjx5auXKlfR2E\/v37q1u3bpoxY4YWLVqkMWPG+L1qJ0k9e\/bUFVdcoWnTplW6bmWv9PkOcnx8vKTATR2zs7M1cewIPT80Xa1TYk9tH4BX+nblFGjS0v164eU3lJFxqtnatWuXJv1ypF4YmqaMlFNDpnM9U2pXToEeXJaj5+YtUtu2bZkOUxM1URM1UdN5UZPb7VZiYqLy8\/PtPqGuq40eysn+yeVylfYzd96iZ69PsXuo2uyf6uvzs2wuofJvjpqoiZqoiZrqf03V7Z\/q9JlSmzdv1sGDB\/XjH\/\/Yjnk8Hq1fv16zZs3Su+++q+LiYuXl5fm90peTk6PU1NQq142KilJUVFSFeFhYmMLCwvxivge8vOrGLat0+OOSV2HyVti+slhVcatc3NeAWZbll7cvB0um0nVKR0wVZ5GuKnLxxV3yyuvx2DWVf6zs3GsQL5\/7meLnejzOFKcmaqImajpdnJrOz5qqul9dVhs9lJP9k4\/X46m0h6qN\/inQufNvjpqoiZrOJk5N1BQqNVW3f6rTQ6kBAwbov\/\/9r19szJgx6tChgx5++GE1b95cERERWrVqlYYPHy5JyszM1HfffafevXsHI2UAAICgo4cCAAD1QZ0eSsXFxalz585+sZiYGCUlJdnxsWPHatKkSUpMTFR8fLzuvfde9e7du8qLnAMAAIQ6eigAAFAf1OmhVHW88MILcrlcGj58uIqKijRo0CD96U9\/CnZaAAAAdRo9FAAACLZ6N5Rau3at388NGjTQ7NmzNXv27OAkBAAAUA\/QQwEAgLqm8itcAQAAAAAAALWIoRQAAAAAAAAcx1AKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAceHBTgCh4dChQ3K73QFfNz4+Xk2aNAn4ugAAAAAAILgYSuGcHTp0SPeMGaWiY0cCvnZUXJLmzF\/IYAoAAAAAgBDDUArnzO12q+jYET1webyaJzUM2Lp7jhzXcx8ckdvtZigFAAAAAECIYSiFgGme1FBtUmIDvGrg3xIIAAAAAACCjwudAwAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOMYSgEAAAAAAMBxDKUAAAAAAADgOIZSAAAAAAAAcBxDKQAAAAAAADiOoRQAAAAAAAAcx1AKAAAAAAAAjmMoBQAAAAAAAMeFBzsBAAAAoC44dOiQ3G53rawdHx+vJk2a1MraAADUVwylAAAAcN47dOiQ7hkzSkXHjtTK+lFxSZozfyGDKQAAymAoBQAAgPOe2+1W0bEjeuDyeDVPahjQtfccOa7nPjgit9vNUAoAgDIYSgEAAAD\/p3lSQ7VJia2FlWvnbYEAANRnXOgcAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwXJ0eSk2dOlWXXHKJ4uLi1LRpUw0dOlSZmZl+25w4cULjxo1TUlKSYmNjNXz4cOXk5AQpYwAAgOCjhwIAAPVBnR5KrVu3TuPGjdPHH3+slStXqqSkRFdffbUKCwvtbSZOnKhly5bpzTff1Lp167R\/\/37deOONQcwaAAAguOihAABAfRAe7AROZ8WKFX4\/v\/rqq2ratKk2b96sn\/zkJ8rPz9fLL7+sRYsW6corr5QkzZ8\/Xx07dtTHH3+sSy+9NBhpAwAABBU9FAAAqA\/q9JlS5eXn50uSEhMTJUmbN29WSUmJBg4caG\/ToUMHtWjRQhs2bAhKjgAAAHUNPRQAAKiL6vSZUmV5vV5NmDBBffv2VefOnSVJBw4cUGRkpBISEvy2TUlJ0YEDB6pcq6ioSEVFRfbPbrdbkuTxeOTxeCRJlmXJ5XLJ6\/XKGGNvW1Xc5XLJsqwKcd\/3XrnkKTMDdMlrx8uqKh4mr0y5uO97Y4ydt++xkiQjy2+floxcMvLKkpFVSdylU5lLLhlZZeJeueQKC7Nr8u3T6\/WWxqUKOda0Juv\/tjey7P15vd7SfdTgeNT0OPniZR9HX7zsY3qmeNj\/PT5l475cqopTEzVREzVRU92uqfx69U2geign+yffsXGFhfn1UPWxfyqfF\/\/mqImaqImaqOl8qKm6\/VO9GUqNGzdOX375pT788MNzXmvq1KmaMmVKhXhWVpZiY2MlSY0aNVJaWppycnLsVxclKTk5WcnJydq3b5\/fdRlSU1OVkJCg3bt3q7i42I77DsiRhK7yRETb8YySHQpXiXZGdPLLoV3JNp1UhLIj2tsxlzxqX\/KVCq1Y7Q3PsOPu+HxJ+3XixAnt3LnTjhcUFEiSChukamdEKzveyJurNM8+5YSlK9+VeKomT46SvQe1L7yFCq24UzV59irBe1S7w9uo2Gqg3MbF6tazwK4vKytLXq9Xubm56tbzMnlc38or1znVFGlOqPXJncp3JehQ4\/bq1rNAhw4dUoMGDdS8eXPl5ubq8OHDp2oK0HFq1qyZYmNj7Zrs45SRofDwcL\/HV5LatWunkydPKjs7+1RNLpfat2+vwsJC7d2791RNkZFq3bq18vPz\/Rr9mJgYaqImaqImaqoHNfn+rtZXgeqhnOyfmjVrJknq8uNLdahxgjwRkZLqZ\/8kSbmNixWf8IP9ePFvjpqoiZqoiZpCvabq9k+WKTsiq6PGjx+vt99+W+vXr1dGxqmmYvXq1RowYICOHj3q90pfy5YtNWHCBE2cOLHS9Sp7pc93kOPj4yUFbuqYnZ2tiWNH6Pmh6WqdEntq+wC80rcrp0CTlu7XCy+\/4fe47Nq1S5N+OVIvDE1TRsqpJulcX+nblVOgB5fl6Ll5i9S2bVt78rlr1y49+KtReu76JmqTEhuwM6W+ySnUg8ty9Oz\/LlSbNm3q5XS4bC6hMvGmJmqiJmo632pyu91KTExUfn6+3SfUF4HsoZzsn1wuV2k\/c+ctevb6FLuHqo\/9U9l9znhlsVq1auWfO\/\/mqImaqImaqCkEa6pu\/1Snz5Qyxujee+\/VkiVLtHbtWr\/GQZIuvvhiRUREaNWqVRo+fLgkKTMzU99995169+5d5bpRUVGKioqqEA8LC1NYWJhfzPeAl1fduGWVNi8ueRUmb4XtK4tVFbfKxX0NmGVZfnn7crBkKl3HZb\/Rrny88lx8cZe88no8dk2+fbpcrtJ4JTnWtKZTcWPvz+Vy2TWd6\/E4U7z88T+bePnjcaY4NVFTVTnWNE5N1HQ2cWo6c01V3a8uq40eysn+ycfr8VTaQ9Wn\/qn89\/yboyZqoqbTxamJmkKlpur2T3V6KDVu3DgtWrRIb7\/9tuLi4uxT2Bo1aqTo6Gg1atRIY8eO1aRJk5SYmKj4+Hjde++96t27N58aAwAAzlv0UAAAoD6o00OpOXPmSJL69+\/vF58\/f75uv\/12SdILL7wgl8ul4cOHq6ioSIMGDdKf\/vQnhzMFAACoO+ihAABAfVCnh1LVudxVgwYNNHv2bM2ePduBjAAAAOo+eigAAFAfVP5mQgAAAAAAAKAWMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAx4UHOwEAAADgfHTo0CG53e5aWTs+Pl5NmjSplbUBAAgUhlIAAACAww4dOqR7xoxS0bEjtbJ+VFyS5sxfyGAKAFCnMZQCAAAAHOZ2u1V07IgeuDxezZMaBnTtPUeO67kPjsjtdjOUAgDUaQylUC9xujsAAAgFzZMaqk1KbC2sXDt9EgAAgcRQCvUOp7sDAAAAAFD\/MZRCvcPp7gAAAAAA1H8MpVBvcbo7AAAAAAD1lyvYCQAAAAAAAOD8w1AKAAAAAAAAjmMoBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOI6hFAAAAAAAABzHUAoAAAAAAACOYygFAAAAAAAAxzGUAgAAAAAAgOMYSgEAAAAAAMBxDKUAAAAAAADgOIZSAAAAAAAAcBxDKQAAAAAAADguPNgJAAAAAHDGoUOH5Ha7A75ufHy8mjRpEvB1AQChjaEUAAAAcB44dOiQ7hkzSkXHjgR87ai4JM2Zv5DBFACgRhhKAdVQW68qSryyCAAAnOF2u1V07IgeuDxezZMaBmzdPUeO67kPjsjtdtPTAABqhKEUcAa1+aqixCuLAADAWc2TGqpNSmyAV62dF+8AAKEtZIZSs2fP1h\/\/+EcdOHBAF110kV566SX17Nkz2GkhBNTWq4oSrywCAIKPHgoAAARLSAyl3njjDU2aNElz585Vr169NGPGDA0aNEiZmZlq2rRpsNNDiKidVxUlXlkEAAQLPRRqGxdWBwCcTkgMpZ5\/\/nndeeedGjNmjCRp7ty5+te\/\/qVXXnlFjzzySJCzAwAAqJvooVCbuLA6AOBM6v1Qqri4WJs3b9ajjz5qx1wulwYOHKgNGzYEMTMAAIC6ix4KtY0LqwMAzqTeD6UOHz4sj8ejlJQUv3hKSoq+\/vrrSu9TVFSkoqIi++f8\/HxJ0tGjR+XxeCRJlmXJ5XLJ6\/XKGGNvW1Xc5XLJsqwKcbfbrZKTHm3\/vlDuE54yWXh99yyXXeVxS16ZcvF9R39QyUmP3G63jh49WnGf+4+V26eRJSMjS5JVSbx8Lv7xfUdPyGNK13e73fZj5Xa75THS9v1uuU+UnFNNp+KW9h0tsveXl5dnP+72\/r4vlPvEyXOqqWyOlqS9R4vtfR49elQul6vc\/jz29mdTk3+O0v7cQp30eP2Ooe85duTIEeXl5fmvY1l+z6+ziTdu3FiNGzeW1+v1i+fn5\/s9jwK1z4SEBDVu3LjCv5u8vDzl5eUFpKbyEhISlJCQIJer9Dh4vV57f4GoqXzctz9fzFfr0aNH\/Y7hudRUVuPGjdWoUSO\/WFhYmHJzcyscw0A9ZxITEyv8fsvPz1deXl5AaiovISFBSUlJMsbYz9VAP2fKxss+Z3y\/y6t7\/GridM8ZY4xyc3PP6TlTVbxx48ZKSEio8Hfr6NGjlf67P5uaKttn+d81eXl5ys\/PD\/jxk0qPYWJioizLsv8++ZT9XVCdeFhYmN9zz\/fWo3M9\/nVNTXsoJ\/snl8ulY8eOVfvvb13un0r3eUIlJz06duyYvc\/a6p8kq0LP5nt8T\/U0BTp2oqRW+6eyNRYUm\/97TAPTPxUWnXS8f5Iq\/\/tbW\/2TdOpvYSD+\/p5t\/yTV3t9fp\/unsjX61Gb\/JFX+99fp\/kmqvb+\/lfVPxphq9d01Udk+neifLMtSo0aN\/J4zweifLMtSXl5erf1fLej9k6nn9u3bZySZjz76yC\/+0EMPmZ49e1Z6n8cff9xI4osvvvjiiy+++Kr21549e5xobRxT0x6K\/okvvvjiiy+++Krp15n6p3p\/plRycrLCwsKUk5PjF8\/JyVFqamql93n00Uc1adIk+2ev16vc3FwlJSXJsqxK7+MUt9ut5s2ba8+ePYqPjw9qLrUh1OuTQr\/GUK9PCv0aQ70+KfRrpD5nGWN07NgxpaenBzuVgKppD0X\/FFyhXmOo1yeFfo2hXp8U+jWGen1S6NdYl+qrbv9U74dSkZGRuvjii7Vq1SoNHTpUUmmTtGrVKo0fP77S+0RFRSkqKsovVvaUvLogPj4+6E+i2hTq9UmhX2Oo1yeFfo2hXp8U+jVSn3PKv2UnFNS0h6J\/qhtCvcZQr08K\/RpDvT4p9GsM9fqk0K+xrtRXnf6p3g+lJGnSpEkaPXq0evTooZ49e2rGjBkqLCy0P0kGAAAAFdFDAQCAYAqJodSIESN06NAhPfbYYzpw4IC6deumFStWVLhwJwAAAE6hhwIAAMEUEkMpSRo\/fnyVb9erT6KiovT4449XOD0+VIR6fVLo1xjq9UmhX2Oo1yeFfo3Uh0AKhR7qfHjOhHqNoV6fFPo1hnp9UujXGOr1SaFfY32szzImxD7fGAAAAAAAAHWeK9gJAAAAAAAA4PzDUAoAAAAAAACOYygFAAAAAAAAxzGUqkNmz56tVq1aqUGDBurVq5c++eSTYKcUMFOnTtUll1yiuLg4NW3aVEOHDlVmZmaw06o1zzzzjCzL0oQJE4KdSkDt27dPv\/jFL5SUlKTo6Gh16dJFn376abDTCgiPx6PJkycrIyND0dHRatOmjZ566inV58vurV+\/Xtdff73S09NlWZaWLl3qd7sxRo899pjS0tIUHR2tgQMHaufOncFJ9iycrr6SkhI9\/PDD6tKli2JiYpSenq7bbrtN+\/fvD17CZ+FMx7Csu+++W5ZlacaMGY7ld66qU9\/27dt1ww03qFGjRoqJidEll1yi7777zvlkUaeFag9F\/xQaQrl\/kkKvhwr1\/kkK\/R4q1PsnKbR6KIZSdcQbb7yhSZMm6fHHH9eWLVt00UUXadCgQTp48GCwUwuIdevWady4cfr444+1cuVKlZSU6Oqrr1ZhYWGwUwu4TZs26X\/\/93\/VtWvXYKcSUEePHlXfvn0VERGhd955R1999ZWee+45NW7cONipBcS0adM0Z84czZo1S9u3b9e0adM0ffp0vfTSS8FO7awVFhbqoosu0uzZsyu9ffr06Zo5c6bmzp2rjRs3KiYmRoMGDdKJEycczvTsnK6+48ePa8uWLZo8ebK2bNmit956S5mZmbrhhhuCkOnZO9Mx9FmyZIk+\/vhjpaenO5RZYJypvqysLF122WXq0KGD1q5dqy+++EKTJ09WgwYNHM4UdVko91D0T\/VfqPdPUuj1UKHeP0mh30OFev8khVgPZVAn9OzZ04wbN87+2ePxmPT0dDN16tQgZlV7Dh48aCSZdevWBTuVgDp27Jhp166dWblypenXr5+5\/\/77g51SwDz88MPmsssuC3YatWbw4MHmjjvu8IvdeOONZtSoUUHKKLAkmSVLltg\/e71ek5qaav74xz\/asby8PBMVFWVef\/31IGR4bsrXV5lPPvnESDLffvutM0kFWFU17t271\/zoRz8yX375pWnZsqV54YUXHM8tECqrb8SIEeYXv\/hFcBJCvXE+9VD0T\/VPqPdPxoR2DxXq\/ZMxod9DhXr\/ZEz976E4U6oOKC4u1ubNmzVw4EA75nK5NHDgQG3YsCGImdWe\/Px8SVJiYmKQMwmscePGafDgwX7HMlT885\/\/VI8ePXTTTTepadOm6t69u\/785z8HO62A6dOnj1atWqUdO3ZIkj7\/\/HN9+OGHuvbaa4OcWe3Izs7WgQMH\/J6rjRo1Uq9evUL6945lWUpISAh2KgHj9Xp166236qGHHlKnTp2CnU5Aeb1e\/etf\/1L79u01aNAgNW3aVL169TrtKfg4\/5xvPRT9U\/0T6v2TdH71UOdj\/ySFXg8Vyv2TVP96KIZSdcDhw4fl8XiUkpLiF09JSdGBAweClFXt8Xq9mjBhgvr27avOnTsHO52A+dvf\/qYtW7Zo6tSpwU6lVuzatUtz5sxRu3bt9O677+qee+7RfffdpwULFgQ7tYB45JFHNHLkSHXo0EERERHq3r27JkyYoFGjRgU7tVrh+91yvvzeOXHihB5++GHdcsstio+PD3Y6ATNt2jSFh4frvvvuC3YqAXfw4EEVFBTomWee0TXXXKP33ntPw4YN04033qh169YFOz3UEedTD0X\/VD+Fev8knV891PnWP0mh2UOFcv8k1b8eKjzYCeD8M27cOH355Zf68MMPg51KwOzZs0f333+\/Vq5cWTffpxsAXq9XPXr00B\/+8AdJUvfu3fXll19q7ty5Gj16dJCzO3eLFy\/WwoULtWjRInXq1Elbt27VhAkTlJ6eHhL1nc9KSkp08803yxijOXPmBDudgNm8ebNefPFFbdmyRZZlBTudgPN6vZKkIUOGaOLEiZKkbt266aOPPtLcuXPVr1+\/YKYHOI7+qX4K9f5JoocKZaHYQ4V6\/yTVvx6KM6XqgOTkZIWFhSknJ8cvnpOTo9TU1CBlVTvGjx+v5cuXa82aNWrWrFmw0wmYzZs36+DBg\/rxj3+s8PBwhYeHa926dZo5c6bCw8Pl8XiCneI5S0tL04UXXugX69ixY538BIez8dBDD9mv9HXp0kW33nqrJk6cGLKv3Pp+t4T67x1fM\/Xtt99q5cqVIfMKnyR98MEHOnjwoFq0aGH\/3vn222\/1wAMPqFWrVsFO75wlJycrPDw8pH\/v4NydLz0U\/VP9Fer9k3R+9VDnS\/8khW4PFer9k1T\/eiiGUnVAZGSkLr74Yq1atcqOeb1erVq1Sr179w5iZoFjjNH48eO1ZMkSrV69WhkZGcFOKaAGDBig\/\/73v9q6dav91aNHD40aNUpbt25VWFhYsFM8Z3379q3wMdQ7duxQy5Ytg5RRYB0\/flwul\/+vxLCwMPuVhlCTkZGh1NRUv987brdbGzduDJnfO75maufOnXr\/\/feVlJQU7JQC6tZbb9UXX3zh93snPT1dDz30kN59991gp3fOIiMjdckll4T07x2cu1Dvoeif6J\/qg\/Ophzof+icptHuoUO+fpPrXQ\/H2vTpi0qRJGj16tHr06KGePXtqxowZKiws1JgxY4KdWkCMGzdOixYt0ttvv624uDj7PdeNGjVSdHR0kLM7d3FxcRWu7xATE6OkpKSQue7DxIkT1adPH\/3hD3\/QzTffrE8++UTz5s3TvHnzgp1aQFx\/\/fX6\/e9\/rxYtWqhTp0767LPP9Pzzz+uOO+4IdmpnraCgQN988439c3Z2trZu3arExES1aNFCEyZM0NNPP6127dopIyNDkydPVnp6uoYOHRq8pGvgdPWlpaXpZz\/7mbZs2aLly5fL4\/HYv3cSExMVGRkZrLRr5EzHsHyTGBERodTUVF1wwQVOp3pWzlTfQw89pBEjRugnP\/mJrrjiCq1YsULLli3T2rVrg5c06pxQ7qHon+q\/UO+fpNDroUK9f5JCv4cK9f5JCrEeKrgf\/oeyXnrpJdOiRQsTGRlpevbsaT7++ONgpxQwkir9mj9\/frBTqzWh9pHGxhizbNky07lzZxMVFWU6dOhg5s2bF+yUAsbtdpv777\/ftGjRwjRo0MC0bt3a\/M\/\/\/I8pKioKdmpnbc2aNZX+uxs9erQxpvRjjSdPnmxSUlJMVFSUGTBggMnMzAxu0jVwuvqys7Or\/L2zZs2aYKdebWc6huXVt480rk59L7\/8smnbtq1p0KCBueiii8zSpUuDlzDqrFDtoeifQkMo90\/GhF4PFer9kzGh30OFev9kTGj1UJYxxpz7aAsAAAAAAACoPq4pBQAAAAAAAMcxlAIAAAAAAIDjGEoBAAAAAADAcQylAAAAAAAA4DiGUgAAAAAAAHAcQykAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAWch44fP67hw4crPj5elmUpLy+vwjZPPPGEunXr5nhuwbR7925ZlqWtW7cGO5Vq69+\/vyZMmGD\/3KpVK82YMcPxPF599VUlJCRUeXt1Htu1a9dW+XwEAKAuoIeqHD3U2aOHwvmOoRTggNtvv12WZemZZ57xiy9dulSWZTmez4IFC\/TBBx\/oo48+0vfff69GjRpV2ObBBx\/UqlWrHM\/NKbfffruGDh0a7DQCbtOmTbrrrruqte2ZmiCn9enTx+\/5WNfyAwA4jx6q7qGHqns9Cj0U6jOGUoBDGjRooGnTpuno0aPBTkVZWVnq2LGjOnfurNTU1EqbutjYWCUlJQUhu1OKi4srxIwxOnnyZBCyqT2V1Xm2mjRpooYNGwZsPSdFRkZW+XwEAJy\/6KFqjh6q5uihgOBgKAU4ZODAgUpNTdXUqVNPu90\/\/vEPderUSVFRUWrVqpWee+65Gu\/rdGv0799fzz33nNavXy\/LstS\/f\/9K1yh\/6rnvVbFnn31WaWlpSkpK0rhx41RSUmJvU1RUpIcffljNmzdXVFSU2rZtq5dfftm+fd26derZs6eioqKUlpamRx55xK856t+\/v8aPH68JEyYoOTlZgwYNsk9Hfuedd3TxxRcrKipKH374obxer6ZOnaqMjAxFR0froosu0t\/\/\/ne\/GrZt26af\/vSnio+PV1xcnC6\/\/HJlZWXpiSee0IIFC\/T222\/LsixZlqW1a9f63dcYo7Zt2+rZZ5\/1i2\/dulWWZembb76p9HHzPU5TpkxRkyZNFB8fr7vvvtuvaaqsTkn68ssvde211yo2NlYpKSm69dZbdfjwYft+hYWFuu222xQbG6u0tLRKnxvlTz3Py8vTr371K6WkpKhBgwbq3Lmzli9frrVr12rMmDHKz8+3H4MnnnjCPo4PPvigfvSjHykmJka9evWq8Pi8+uqratGihRo2bKhhw4bpyJEjlT4e5X399dfq06ePncu6devs28qeen66\/P70pz+pXbt2atCggVJSUvSzn\/2sWvsGANRP9FD0UKerU6KHoodCvWYA1LrRo0ebIUOGmLfeess0aNDA7NmzxxhjzJIlS0zZf4affvqpcblc5sknnzSZmZlm\/vz5Jjo62syfP7\/a+zrTGkeOHDF33nmn6d27t\/n+++\/NkSNHKl3n8ccfNxdddJFfDfHx8ebuu+8227dvN8uWLTMNGzY08+bNs7e5+eabTfPmzc1bb71lsrKyzPvvv2\/+9re\/GWOM2bt3r2nYsKH59a9\/bbZv326WLFlikpOTzeOPP27fv1+\/fiY2NtY89NBD5uuvvzZff\/21WbNmjZFkunbtat577z3zzTffmCNHjpinn37adOjQwaxYscJkZWWZ+fPnm6ioKLN27Vp7f4mJiebGG280mzZtMpmZmeaVV14xX3\/9tTl27Ji5+eabzTXXXGO+\/\/578\/3335uioiKTnZ1tJJnPPvvMGGPM73\/\/e3PhhRf6PS733Xef+clPflLl4z969GgTGxtrRowYYb788kuzfPly06RJE\/Pb3\/72tHUePXrUNGnSxDz66KNm+\/btZsuWLeaqq64yV1xxhX2\/e+65x7Ro0cK8\/\/775osvvjA\/\/elPTVxcnLn\/\/vvtbVq2bGleeOEFY4wxHo\/HXHrppaZTp07mvffeM1lZWWbZsmXm3\/\/+tykqKjIzZsww8fHx9mNw7NgxY4wxv\/zlL02fPn3M+vXrzTfffGP++Mc\/mqioKLNjxw5jjDEff\/yxcblcZtq0aSYzM9O8+OKLJiEhwTRq1KjKx8X32DZr1sz8\/e9\/N1999ZX55S9\/aeLi4szhw4eNMcY+1kePHq0yv02bNpmwsDCzaNEis3v3brNlyxbz4osvVrlfAED9Rg9FD0UPRQ+F0MZQCnCAr6EyxphLL73U3HHHHcaYig3Vz3\/+c3PVVVf53fehhx6q8Ef9dKqzxv3332\/69et32nUqa6hatmxpTp48acduuukmM2LECGOMMZmZmUaSWblyZaXr\/fa3vzUXXHCB8Xq9dmz27NkmNjbWeDweY0xpo9G9e3e\/+\/n+yC5dutSOnThxwjRs2NB89NFHftuOHTvW3HLLLcYYYx599FGTkZFhiouLK82n7DHxKd9Q7du3z4SFhZmNGzcaY4wpLi42ycnJ5tVXX610Td+6iYmJprCw0I7NmTPnjHU+9dRT5uqrr\/aL7dmzx0gymZmZ5tixYyYyMtIsXrzYvv3IkSMmOjq6yobq3XffNS6Xy2RmZlaa6\/z58ys0Qd9++60JCwsz+\/bt84sPGDDAPProo8YYY2655RZz3XXX+d0+YsSIajVUzzzzjB0rKSkxzZo1M9OmTTPG+DdUVeX3j3\/8w8THxxu3213lvgAAoYMeih6KHooeCqGNt+8BDps2bZoWLFig7du3V7ht+\/bt6tu3r1+sb9++2rlzpzweT7XWD8QaVenUqZPCwsLsn9PS0nTw4EFJpadkh4WFqV+\/flXm1bt3b7\/3uvft21cFBQXau3evHbv44osrvX+PHj3s77\/55hsdP35cV111lWJjY+2v1157TVlZWXY+l19+uSIiIs663vT0dA0ePFivvPKKJGnZsmUqKirSTTfddNr7XXTRRX7XJOjdu7cKCgq0Z8+eKuv8\/PPPtWbNGr96OnToIKn0+hVZWVkqLi5Wr1697PskJibqggsuqDKPrVu3qlmzZmrfvn21a\/7vf\/8rj8ej9u3b++Wybt06+7Hdvn27Xx6+Gquj7Hbh4eHq0aNHpf8WqnLVVVepZcuWat26tW699VYtXLhQx48fr\/b9AQD1Fz0UPVRlddJDVQ89FOqq8GAnAJxvfvKTn2jQoEF69NFHdfvttwc7nRop35xYliWv1ytJio6ODsg+YmJizhgvKCiQJP3rX\/\/Sj370I7\/toqKiAprPL3\/5S91666164YUXNH\/+fI0YMSIgF8EsX2dBQYGuv\/56TZs2rcK2aWlpVV5\/4XTO5jEoKChQWFiYNm\/e7Nc8S6UXbg22uLg4bdmyRWvXrtV7772nxx57TE888YQ2bdrEp8wAQIijhzo9eih6qNOhh0JdxZlSQBA888wzWrZsmTZs2OAX79ixo\/7zn\/\/4xf7zn\/+offv2Ff64VSUQa5yNLl26yOv1+l10sXxeGzZskDHGL6+4uDg1a9asRvu68MILFRUVpe+++05t27b1+2revLkkqWvXrvrggw\/8LiJaVmRkZLVe9bzuuusUExOjOXPmaMWKFbrjjjvOeJ\/PP\/9cP\/zwg\/3zxx9\/rNjYWDu3yvz4xz\/Wtm3b1KpVqwo1xcTEqE2bNoqIiNDGjRvt+xw9elQ7duyocs2uXbtq7969VW5T2WPQvXt3eTweHTx4sEIeqampkkqPZdk8fDVWR9ntTp48qc2bN6tjx47Vzk8qfXVw4MCBmj59ur744gvt3r1bq1evrtb+AQD1Gz3UqbzooUrRQ1UvP4keCnUTQykgCLp06aJRo0Zp5syZfvEHHnhAq1at0lNPPaUdO3ZowYIFmjVrlh588EF7mwEDBmjWrFlVrl2dNWpDq1atNHr0aN1xxx1aunSpsrOztXbtWi1evFiS9Otf\/1p79uzRvffeq6+\/\/lpvv\/22Hn\/8cU2aNEkuV81+FcXFxenBBx\/UxIkTtWDBAmVlZWnLli166aWXtGDBAknS+PHj5Xa7NXLkSH366afauXOn\/vKXvygzM9PO94svvlBmZqYOHz5cZeMVFham22+\/XY8++qjatWtXrVOsi4uLNXbsWH311Vf697\/\/rccff1zjx48\/bZ3jxo1Tbm6ubrnlFm3atElZWVl69913NWbMGHk8HsXGxmrs2LF66KGHtHr1an355Ze6\/fbbT7tmv3799JOf\/ETDhw\/XypUrlZ2drXfeeUcrVqywH4OCggKtWrVKhw8f1vHjx9W+fXuNGjVKt912m9566y1lZ2frk08+0dSpU\/Wvf\/1LknTfffdpxYoVevbZZ7Vz507NmjXLXvNMZs+erSVLlujrr7\/WuHHjdPTo0Sqb1MryW758uWbOnKmtW7fq22+\/1WuvvSav13vaU\/ABAKGDHooeqjx6qIrooVCvBPuiVsD5oKoLQkZGRpry\/wz\/\/ve\/mwsvvNBERESYFi1amD\/+8Y9+t7ds2dLv01Yqc6Y1zvYineVrKL\/ODz\/8YCZOnGjS0tJMZGSkadu2rXnllVfs29euXWsuueQSExkZaVJTU83DDz9sSkpK7Nv79evnd8FJYypeuNHH6\/WaGTNmmAsuuMBERESYJk2amEGDBpl169bZ23z++efm6quvNg0bNjRxcXHm8ssvN1lZWcYYYw4ePGiuuuoqExsbaySZNWvWVLhIp09WVpaRZKZPn37ax6zs4\/TYY4+ZpKQkExsba+68805z4sSJ09ZpjDE7duwww4YNMwkJCSY6Otp06NDBTJgwwb6w6bFjx8wvfvEL07BhQ5OSkmKmT59eYa2yF+k0pvRCnmPGjDFJSUmmQYMGpnPnzmb58uX27XfffbdJSkoykuznVXFxsXnsscdMq1atTEREhElLSzPDhg0zX3zxhX2\/l19+2TRr1sxER0eb66+\/3jz77LPVukjnokWLTM+ePU1kZKS58MILzerVq+1tKjvW5fP74IMPTL9+\/Uzjxo1NdHS06dq1q3njjTfOcFQAAPUVPVQpeqiq6zSGHooeCvWZZUyZ80ABABV88MEHGjBggPbs2aOUlJTTbnv77bcrLy9PS5cudSY5AACAOooeCsCZcKFzAKhCUVGRDh06pCeeeEI33XTTGZspAAAA0EMBqD6uKQUAVXj99dfVsmVL5eXlafr06cFOBwAAoF6ghwJQXbx9DwAAAAAAAI7jTCkAAAAAAAA4jqEUAAAAAAAAHMdQCgAAAAAAAI5jKAUAAAAAAADHMZQCAAAAAACA4xhKAQAAAAAAwHEMpQAAAAAAAOA4hlIAAAAAAABwHEMpAAAAAAAAOO7\/A8HsvAjeCp9HAAAAAElFTkSuQmCC\" \/><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>CD-1\u5b66\u7fd2\u306eRBM\u306f\u30c7\u30fc\u30bf\u306b\u3088\u3063\u3066\u306f16\u30d3\u30c3\u30c8\u9593\u9055\u3048\u308b\u3053\u3068\u304c\u3042\u308b\u4e00\u65b9\u3067\u3001SA\u5b66\u7fd2\u306eRBM\u306f\u8aa4\u308a\u30924\u30d3\u30c3\u30c8\u307e\u3067\u306b\u6291\u3048\u3089\u308c\u3066\u3044\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h3><span class=\"ez-toc-section\" id=\"%E5%AE%9F%E9%A8%933_%E5%AF%BE%E6%95%B0%E5%B0%A4%E5%BA%A6%E6%AF%94%E8%BC%83\"><\/span>\u5b9f\u9a133 \u5bfe\u6570\u5c24\u5ea6\u6bd4\u8f03<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u6700\u5f8c\u306b\u5bfe\u6570\u5c24\u5ea6\u306e\u6bd4\u8f03\u3092\u884c\u3044\u307e\u3059\u3002\u8a08\u7b97\u91cf\u3092\u6e1b\u3089\u3059\u305f\u3081\u3001\u96a0\u308c\u5c64\u306e\u30ce\u30fc\u30c9\u6570\u309220\u306b\u8a2d\u5b9a\u3057\u76f4\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"c1\"># \u30d1\u30e9\u30e1\u30fc\u30bf\u8a2d\u5b9a<\/span>\r\n<span class=\"n\">n_visible<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">64<\/span>\r\n<span class=\"n\">n_hidden<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">20<\/span> <span class=\"c1\"># \u96a0\u308c\u5c64\u306e\u30ce\u30fc\u30c9\u3092\u6e1b\u3089\u3059<\/span>\r\n<span class=\"n\">epochs<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">400<\/span>\r\n<span class=\"n\">batch_size<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">64<\/span>\r\n\r\n<span class=\"c1\"># \u5c24\u5ea6\u8a08\u7b97\u7528\u306e\u5168\u96a0\u308c\u72b6\u614b\u306e\u751f\u6210 (2^20\u901a\u308a)<\/span>\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"Generating <\/span><span class=\"si\">{<\/span><span class=\"mi\">1<\/span><span class=\"w\"> <\/span><span class=\"o\">&lt;&lt;<\/span><span class=\"w\"> <\/span><span class=\"n\">n_hidden<\/span><span class=\"si\">}<\/span><span class=\"s2\"> hidden states...\"<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">indices<\/span> <span class=\"o\">=<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">arange<\/span><span class=\"p\">(<\/span><span class=\"mi\">1<\/span> <span class=\"o\">&lt;&lt;<\/span> <span class=\"n\">n_hidden<\/span><span class=\"p\">,<\/span> <span class=\"n\">dtype<\/span><span class=\"o\">=<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">uint32<\/span><span class=\"p\">)[:,<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">newaxis<\/span><span class=\"p\">]<\/span>\r\n<span class=\"n\">bit_masks<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">1<\/span> <span class=\"o\">&lt;&lt;<\/span> <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">arange<\/span><span class=\"p\">(<\/span><span class=\"n\">n_hidden<\/span><span class=\"p\">,<\/span> <span class=\"n\">dtype<\/span><span class=\"o\">=<\/span><span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">uint32<\/span><span class=\"p\">)[::<\/span><span class=\"o\">-<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span>\r\n<span class=\"n\">all_hidden_states<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">indices<\/span> <span class=\"o\">&amp;<\/span> <span class=\"n\">bit_masks<\/span> <span class=\"o\">&gt;<\/span> <span class=\"mi\">0<\/span><span class=\"p\">)<\/span><span class=\"o\">.<\/span><span class=\"n\">astype<\/span><span class=\"p\">(<\/span><span class=\"nb\">float<\/span><span class=\"p\">)<\/span>\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"Done.\"<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u6bd4\u8f03\u7528\u306e2\u3064\u306e\u30e2\u30c7\u30eb\u3092\u521d\u671f\u5316<\/span>\r\n<span class=\"n\">rbm_cd2<\/span> <span class=\"o\">=<\/span> <span class=\"n\">IntegratedRBM<\/span><span class=\"p\">(<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_hidden<\/span><span class=\"p\">,<\/span> <span class=\"n\">learning_rate<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.10<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">rbm_sa2<\/span> <span class=\"o\">=<\/span> <span class=\"n\">IntegratedRBM<\/span><span class=\"p\">(<\/span><span class=\"n\">n_visible<\/span><span class=\"p\">,<\/span> <span class=\"n\">n_hidden<\/span><span class=\"p\">,<\/span> <span class=\"n\">learning_rate<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.10<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u5c65\u6b74\u4fdd\u5b58\u7528\u306e\u30ea\u30b9\u30c8\u3092\u8ffd\u52a0<\/span>\r\n<span class=\"n\">ll_history_cd<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n<span class=\"n\">ll_history_sa<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n<span class=\"n\">epoch_list<\/span> <span class=\"o\">=<\/span> <span class=\"p\">[]<\/span>\r\n\r\n<span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"Starting Training Comparison...\"<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"k\">for<\/span> <span class=\"n\">epoch<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">epochs<\/span> <span class=\"o\">+<\/span> <span class=\"mi\">1<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">np<\/span><span class=\"o\">.<\/span><span class=\"n\">random<\/span><span class=\"o\">.<\/span><span class=\"n\">shuffle<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># \u30d0\u30c3\u30c1\u5b66\u7fd2<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">i<\/span> <span class=\"ow\">in<\/span> <span class=\"nb\">range<\/span><span class=\"p\">(<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"nb\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">),<\/span> <span class=\"n\">batch_size<\/span><span class=\"p\">):<\/span>\r\n        <span class=\"n\">batch<\/span> <span class=\"o\">=<\/span> <span class=\"n\">train_data<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">:<\/span><span class=\"n\">i<\/span><span class=\"o\">+<\/span><span class=\"n\">batch_size<\/span><span class=\"p\">]<\/span>\r\n\r\n        <span class=\"c1\"># \u305d\u308c\u305e\u308c\u72ec\u7acb\u3057\u305f\u30e2\u30c7\u30eb\u3068\u3057\u3066\u5b66\u7fd2<\/span>\r\n        <span class=\"n\">rbm_cd2<\/span><span class=\"o\">.<\/span><span class=\"n\">train_step_cd<\/span><span class=\"p\">(<\/span><span class=\"n\">batch<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">rbm_sa2<\/span><span class=\"o\">.<\/span><span class=\"n\">train_step_sa<\/span><span class=\"p\">(<\/span><span class=\"n\">batch<\/span><span class=\"p\">,<\/span> <span class=\"n\">num_reads<\/span><span class=\"o\">=<\/span><span class=\"n\">batch_size<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"c1\"># 10\u30a8\u30dd\u30c3\u30af\u3054\u3068\u306b\u5c24\u5ea6\u3092\u8a08\u7b97\u3057\u3066\u6bd4\u8f03<\/span>\r\n    <span class=\"k\">if<\/span> <span class=\"n\">epoch<\/span> <span class=\"o\">%<\/span> <span class=\"mi\">10<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">0<\/span> <span class=\"ow\">or<\/span> <span class=\"n\">epoch<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">1<\/span><span class=\"p\">:<\/span>\r\n        <span class=\"c1\"># \u4e21\u30e2\u30c7\u30eb\u306e\u5bfe\u6570\u5c24\u5ea6\u3092\u7b97\u51fa<\/span>\r\n        <span class=\"n\">ll_cd<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rbm_cd2<\/span><span class=\"o\">.<\/span><span class=\"n\">get_log_likelihood<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">all_hidden_states<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">ll_sa<\/span> <span class=\"o\">=<\/span> <span class=\"n\">rbm_sa2<\/span><span class=\"o\">.<\/span><span class=\"n\">get_log_likelihood<\/span><span class=\"p\">(<\/span><span class=\"n\">train_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">all_hidden_states<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"c1\"># \u30c7\u30fc\u30bf\u306e\u4fdd\u5b58<\/span>\r\n        <span class=\"n\">epoch_list<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">epoch<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">ll_history_cd<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">ll_cd<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">ll_history_sa<\/span><span class=\"o\">.<\/span><span class=\"n\">append<\/span><span class=\"p\">(<\/span><span class=\"n\">ll_sa<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"nb\">print<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"Epoch <\/span><span class=\"si\">{<\/span><span class=\"n\">epoch<\/span><span class=\"si\">:<\/span><span class=\"s2\">3d<\/span><span class=\"si\">}<\/span><span class=\"s2\">: CD LL=<\/span><span class=\"si\">{<\/span><span class=\"n\">ll_cd<\/span><span class=\"si\">:<\/span><span class=\"s2\">.2f<\/span><span class=\"si\">}<\/span><span class=\"s2\">, SA LL=<\/span><span class=\"si\">{<\/span><span class=\"n\">ll_sa<\/span><span class=\"si\">:<\/span><span class=\"s2\">.2f<\/span><span class=\"si\">}<\/span><span class=\"s2\">\"<\/span><span class=\"p\">)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_subarea output_stream output_stdout output_text\">\n<pre>Generating 1048576 hidden states...\r\nDone.\r\nStarting Training Comparison...\r\nEpoch   1: CD LL=-44.46, SA LL=-44.46\r\nEpoch  10: CD LL=-44.29, SA LL=-43.84\r\nEpoch  20: CD LL=-43.86, SA LL=-43.75\r\nEpoch  30: CD LL=-43.08, SA LL=-43.61\r\nEpoch  40: CD LL=-40.78, SA LL=-43.41\r\nEpoch  50: CD LL=-38.06, SA LL=-43.15\r\nEpoch  60: CD LL=-35.56, SA LL=-42.87\r\nEpoch  70: CD LL=-33.28, SA LL=-42.65\r\nEpoch  80: CD LL=-31.34, SA LL=-42.23\r\nEpoch  90: CD LL=-29.88, SA LL=-41.25\r\nEpoch 100: CD LL=-28.43, SA LL=-39.59\r\nEpoch 110: CD LL=-27.32, SA LL=-37.56\r\nEpoch 120: CD LL=-26.05, SA LL=-35.62\r\nEpoch 130: CD LL=-25.18, SA LL=-33.88\r\nEpoch 140: CD LL=-24.65, SA LL=-32.13\r\nEpoch 150: CD LL=-24.12, SA LL=-30.50\r\nEpoch 160: CD LL=-23.09, SA LL=-28.87\r\nEpoch 170: CD LL=-22.83, SA LL=-27.31\r\nEpoch 180: CD LL=-22.27, SA LL=-25.93\r\nEpoch 190: CD LL=-22.00, SA LL=-24.63\r\nEpoch 200: CD LL=-21.69, SA LL=-23.33\r\nEpoch 210: CD LL=-21.57, SA LL=-22.15\r\nEpoch 220: CD LL=-21.88, SA LL=-21.04\r\nEpoch 230: CD LL=-21.23, SA LL=-20.12\r\nEpoch 240: CD LL=-21.53, SA LL=-19.23\r\nEpoch 250: CD LL=-21.25, SA LL=-18.52\r\nEpoch 260: CD LL=-20.87, SA LL=-17.85\r\nEpoch 270: CD LL=-21.16, SA LL=-17.30\r\nEpoch 280: CD LL=-20.88, SA LL=-16.87\r\nEpoch 290: CD LL=-21.28, SA LL=-16.51\r\nEpoch 300: CD LL=-20.76, SA LL=-16.32\r\nEpoch 310: CD LL=-20.92, SA LL=-15.78\r\nEpoch 320: CD LL=-21.03, SA LL=-15.74\r\nEpoch 330: CD LL=-20.78, SA LL=-15.52\r\nEpoch 340: CD LL=-21.53, SA LL=-15.46\r\nEpoch 350: CD LL=-21.60, SA LL=-15.13\r\nEpoch 360: CD LL=-21.34, SA LL=-15.36\r\nEpoch 370: CD LL=-21.06, SA LL=-14.94\r\nEpoch 380: CD LL=-21.93, SA LL=-14.94\r\nEpoch 390: CD LL=-22.89, SA LL=-15.29\r\nEpoch 400: CD LL=-24.01, SA LL=-14.98\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u6c42\u3081\u305f\u30a8\u30dd\u30c3\u30af\u6bce\u306e\u5bfe\u6570\u5c24\u5ea6\u3092\u30b0\u30e9\u30d5\u306b\u63cf\u5199\u3057\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing code_cell rendered\">\n<div class=\"input\">\n<div class=\"inner_cell\">\n<div class=\"input_area\">\n<div class=\"highlight hl-python\">\n<pre><span><\/span><span class=\"c1\"># 5. \u5bfe\u6570\u5c24\u5ea6\u306e\u63a8\u79fb\u3092\u63cf\u5199<\/span>\r\n\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">figure<\/span><span class=\"p\">(<\/span><span class=\"n\">figsize<\/span><span class=\"o\">=<\/span><span class=\"p\">(<\/span><span class=\"mi\">8<\/span><span class=\"p\">,<\/span> <span class=\"mi\">6<\/span><span class=\"p\">))<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">plot<\/span><span class=\"p\">(<\/span><span class=\"n\">epoch_list<\/span><span class=\"p\">,<\/span> <span class=\"n\">ll_history_cd<\/span><span class=\"p\">,<\/span> <span class=\"s1\">'o-'<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"o\">=<\/span><span class=\"s1\">'black'<\/span><span class=\"p\">,<\/span> <span class=\"n\">label<\/span><span class=\"o\">=<\/span><span class=\"s1\">'CD-1'<\/span><span class=\"p\">,<\/span> <span class=\"n\">markersize<\/span><span class=\"o\">=<\/span><span class=\"mi\">4<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">plot<\/span><span class=\"p\">(<\/span><span class=\"n\">epoch_list<\/span><span class=\"p\">,<\/span> <span class=\"n\">ll_history_sa<\/span><span class=\"p\">,<\/span> <span class=\"s1\">'s-'<\/span><span class=\"p\">,<\/span> <span class=\"n\">color<\/span><span class=\"o\">=<\/span><span class=\"s1\">'red'<\/span><span class=\"p\">,<\/span> <span class=\"n\">label<\/span><span class=\"o\">=<\/span><span class=\"s1\">'SA (OpenJij)'<\/span><span class=\"p\">,<\/span> <span class=\"n\">markersize<\/span><span class=\"o\">=<\/span><span class=\"mi\">4<\/span><span class=\"p\">)<\/span>\r\n\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">xlabel<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"Epoch\"<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">ylabel<\/span><span class=\"p\">(<\/span><span class=\"s2\">\"Log-likelihood\"<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">title<\/span><span class=\"p\">(<\/span><span class=\"sa\">f<\/span><span class=\"s2\">\"Log-likelihood Comparison\"<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">legend<\/span><span class=\"p\">()<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">grid<\/span><span class=\"p\">(<\/span><span class=\"kc\">True<\/span><span class=\"p\">,<\/span> <span class=\"n\">linestyle<\/span><span class=\"o\">=<\/span><span class=\"s1\">'--'<\/span><span class=\"p\">,<\/span> <span class=\"n\">alpha<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.5<\/span><span class=\"p\">)<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">tight_layout<\/span><span class=\"p\">()<\/span>\r\n<span class=\"n\">plt<\/span><span class=\"o\">.<\/span><span class=\"n\">show<\/span><span class=\"p\">()<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"output_wrapper\">\n<div class=\"output\">\n<div class=\"output_area\">\n<div class=\"prompt\"><\/div>\n<div class=\"output_png output_subarea\"><img decoding=\"async\" alt=\"No description has been provided for this image\" src=\"data:image\/png;base64,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\" \/><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>200\u30a8\u30dd\u30c3\u30af\u3067CD-1\u306e\u5bfe\u6570\u5c24\u5ea6\u304c\u4e00\u5b9a\u306b\u306a\u308a\u3001SA\u306f\u3055\u3089\u306b\u5927\u304d\u304f\u306a\u3063\u3066400\u30a8\u30dd\u30c3\u30af\u3067\u4e00\u5b9a\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h2><span class=\"ez-toc-section\" id=\"%E3%81%BE%E3%81%A8%E3%82%81\"><\/span>\u307e\u3068\u3081<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5143\u8ad6\u6587\u306eCD-1\u5b66\u7fd2\u306eRBM\u3068QA\u5b66\u7fd2\u306eRBM\u3092\u5b9f\u88c5\u3057\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3001\u753b\u50cf\u518d\u69cb\u6210\u3001\u5bfe\u6570\u5c24\u5ea6\u306e\u6bd4\u8f03\u3092\u884c\u3044\u307e\u3057\u305f\u3002\u691c\u8a3c\u3057\u305f\u7d50\u679c\u30013\u3064\u306e\u5b9f\u9a13\u306b\u304a\u3044\u3066\u3001\u8ad6\u6587\u306e\u5831\u544a\u3068\u306f\u7570\u306a\u308b\u7d50\u679c\u306b\u306a\u308a\u307e\u3057\u305f\u3002\u539f\u56e0\u306f\u3001QA\u306e\u4ee3\u308f\u308a\u306b\u7528\u3044\u305fSA\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u65b9\u6cd5\u306b\u3042\u308b\u3068\u601d\u308f\u308c\u307e\u3059\u3002\u5b9f\u9a13\u7d50\u679c\u304b\u3089QA\u3068SA\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306f\u7570\u306a\u308b\u632f\u821e\u3044\u3092\u3057\u3001SA\u306b\u3088\u308b\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u306fCD-1\u3088\u308a\u3082\u771f\u306e\u78ba\u7387\u5206\u5e03\u3092\u6a21\u5023\u3067\u304d\u3066\u3044\u308b\u3068\u8a00\u3048\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<h2><span class=\"ez-toc-section\" id=\"%E3%81%82%E3%81%A8%E3%81%8C%E3%81%8D\"><\/span>\u3042\u3068\u304c\u304d<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"cell border-box-sizing text_cell rendered\">\n<div class=\"inner_cell\">\n<div class=\"text_cell_render border-box-sizing rendered_html\">\n<p>RBM\u306e\u7406\u8ad6\u3092\u5b66\u3076\u3060\u3051\u3067\u306a\u304f\u5b9f\u88c5\u306b\u3082\u53d6\u308a\u7d44\u3093\u3060\u3053\u3068\u3067\u3001RBM\u306e\u4ed5\u7d44\u307f\u306b\u3064\u3044\u3066\u7406\u89e3\u3092\u6df1\u3081\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3057\u305f\u3002\u307e\u305f\u3001SA\u5b66\u7fd2\u306eRBM\u306fQA\u3068\u306f\u7570\u306a\u308b\u7d50\u679c\u3092\u793a\u3057\u305f\u306e\u3067\u3001QA\u306b\u3088\u308a\u8fd1\u3044\u632f\u821e\u3044\u3092\u3059\u308b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u91cf\u5b50\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SQA)\u3092\u4f7f\u3063\u3066RBM\u3092\u5b66\u7fd2\u3057\u305f\u5834\u5408\u3068\u6bd4\u8f03\u3057\u3066\u307f\u305f\u3044\u3068\u601d\u3044\u307e\u3057\u305f\u3002<span style=\"font-family: Consolas, Monaco, monospace;\"><\/span><\/p>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u6982\u8981 \u89e3\u8aac\u8a18\u4e8b\u300cD-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088 [&hellip;]<\/p>\n","protected":false},"author":19,"featured_media":9247,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[47,65,317,122],"class_list":["post-9070","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-hands-on","tag-47","tag-65","tag-317","tag-122"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2 - T-QARD Harbor<\/title>\n<meta name=\"description\" content=\"\u89e3\u8aac\u8a18\u4e8b\u300cD-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088\u3073\u5bfe\u6570\u5c24\u5ea6\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3059\u308b\u3068\u3044\u3046\u8ad6\u6587\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5b9f\u969b\u306b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3001\u5143\u8ad6\u6587\u306e\u518d\u73fe\u5b9f\u9a13\u3092\u884c\u3044\u307e\u3059\u3002\u4eca\u56de\u306fQA\u306e\u4ee3\u308f\u308a\u306b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3092\u7528\u3044\u307e\u3057\u305f\u3002\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/\u3010\u5b9f\u8df5\u7de8\u3011d-wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\/\" \/>\n<meta property=\"og:locale\" content=\"ja_JP\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2 - T-QARD Harbor\" \/>\n<meta property=\"og:description\" content=\"\u89e3\u8aac\u8a18\u4e8b\u300cD-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088\u3073\u5bfe\u6570\u5c24\u5ea6\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3059\u308b\u3068\u3044\u3046\u8ad6\u6587\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5b9f\u969b\u306b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3001\u5143\u8ad6\u6587\u306e\u518d\u73fe\u5b9f\u9a13\u3092\u884c\u3044\u307e\u3059\u3002\u4eca\u56de\u306fQA\u306e\u4ee3\u308f\u308a\u306b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3092\u7528\u3044\u307e\u3057\u305f\u3002\" \/>\n<meta property=\"og:url\" content=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/\u3010\u5b9f\u8df5\u7de8\u3011d-wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\/\" \/>\n<meta property=\"og:site_name\" content=\"T-QARD Harbor\" \/>\n<meta property=\"article:published_time\" content=\"2026-06-17T06:21:55+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-06-17T06:27:45+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-content\/uploads\/2026\/06\/e86a20425456acedcd5efa7cbfa66cb0.png\" \/>\n\t<meta property=\"og:image:width\" content=\"420\" \/>\n\t<meta property=\"og:image:height\" content=\"301\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Moriaki Shimazaki\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u57f7\u7b46\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"Moriaki Shimazaki\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u63a8\u5b9a\u8aad\u307f\u53d6\u308a\u6642\u9593\" \/>\n\t<meta name=\"twitter:data2\" content=\"61\u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/\"},\"author\":{\"name\":\"Moriaki Shimazaki\",\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/#\\\/schema\\\/person\\\/6adf10ecefe2a32c11ddbe87f4b69ff4\"},\"headline\":\"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\",\"datePublished\":\"2026-06-17T06:21:55+00:00\",\"dateModified\":\"2026-06-17T06:27:45+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/\"},\"wordCount\":604,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/e86a20425456acedcd5efa7cbfa66cb0.png\",\"keywords\":[\"\u30ae\u30d6\u30b9\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\",\"\u30dc\u30eb\u30c4\u30de\u30f3\u6a5f\u68b0\u5b66\u7fd2\",\"\u5236\u9650\u4ed8\u304d\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\",\"\u91cf\u5b50\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0\"],\"articleSection\":[\"\u5b9f\u8df5\u8a18\u4e8b\"],\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/\",\"url\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/\",\"name\":\"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2 - T-QARD Harbor\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/e86a20425456acedcd5efa7cbfa66cb0.png\",\"datePublished\":\"2026-06-17T06:21:55+00:00\",\"dateModified\":\"2026-06-17T06:27:45+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/#\\\/schema\\\/person\\\/6adf10ecefe2a32c11ddbe87f4b69ff4\"},\"description\":\"\u89e3\u8aac\u8a18\u4e8b\u300cD-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088\u3073\u5bfe\u6570\u5c24\u5ea6\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3059\u308b\u3068\u3044\u3046\u8ad6\u6587\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5b9f\u969b\u306b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3001\u5143\u8ad6\u6587\u306e\u518d\u73fe\u5b9f\u9a13\u3092\u884c\u3044\u307e\u3059\u3002\u4eca\u56de\u306fQA\u306e\u4ee3\u308f\u308a\u306b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3092\u7528\u3044\u307e\u3057\u305f\u3002\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#breadcrumb\"},\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#primaryimage\",\"url\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/e86a20425456acedcd5efa7cbfa66cb0.png\",\"contentUrl\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/e86a20425456acedcd5efa7cbfa66cb0.png\",\"width\":420,\"height\":301},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/2026\\\/06\\\/17\\\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u30db\u30fc\u30e0\",\"item\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/#website\",\"url\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/\",\"name\":\"T-QARD Harbor\",\"description\":\"T-QARD Harbor\u306f\u6771\u5317\u5927\u5b66\u91cf\u5b50\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u7814\u7a76\u958b\u767a\u30bb\u30f3\u30bf\u30fc\u5b66\u751f\u30c1\u30fc\u30e0\u300cT-QARD Crews\u300d\u304c\u904b\u55b6\u3059\u308b\u3001 \u6570\u7406\u60c5\u5831\u7d71\u8a08\u3001\u91cf\u5b50\u60c5\u5831\u3001\u6700\u9069\u5316\u3001\u6a5f\u68b0\u5b66\u7fd2\u5206\u91ce\u306e\u60c5\u5831\u3092\u63d0\u4f9b\u3059\u308bWeb\u30b5\u30a4\u30c8\u3067\u3059\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ja\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/#\\\/schema\\\/person\\\/6adf10ecefe2a32c11ddbe87f4b69ff4\",\"name\":\"Moriaki Shimazaki\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/ff04e3ac806c71c8384f4aba5b01894a7a3c6ab04904ae7fea5358b02cb15135?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/ff04e3ac806c71c8384f4aba5b01894a7a3c6ab04904ae7fea5358b02cb15135?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/ff04e3ac806c71c8384f4aba5b01894a7a3c6ab04904ae7fea5358b02cb15135?s=96&d=mm&r=g\",\"caption\":\"Moriaki Shimazaki\"},\"description\":\"\u6771\u5317\u5927\u5b66 \u5de5\u5b66\u90e8 \u5b66\u58eb\u8ab2\u7a0b\",\"url\":\"https:\\\/\\\/qard.is.tohoku.ac.jp\\\/T-Wave\\\/author\\\/moriaki-shimazaki\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2 - T-QARD Harbor","description":"\u89e3\u8aac\u8a18\u4e8b\u300cD-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088\u3073\u5bfe\u6570\u5c24\u5ea6\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3059\u308b\u3068\u3044\u3046\u8ad6\u6587\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5b9f\u969b\u306b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3001\u5143\u8ad6\u6587\u306e\u518d\u73fe\u5b9f\u9a13\u3092\u884c\u3044\u307e\u3059\u3002\u4eca\u56de\u306fQA\u306e\u4ee3\u308f\u308a\u306b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3092\u7528\u3044\u307e\u3057\u305f\u3002","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/\u3010\u5b9f\u8df5\u7de8\u3011d-wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\/","og_locale":"ja_JP","og_type":"article","og_title":"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2 - T-QARD Harbor","og_description":"\u89e3\u8aac\u8a18\u4e8b\u300cD-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088\u3073\u5bfe\u6570\u5c24\u5ea6\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3059\u308b\u3068\u3044\u3046\u8ad6\u6587\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5b9f\u969b\u306b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3001\u5143\u8ad6\u6587\u306e\u518d\u73fe\u5b9f\u9a13\u3092\u884c\u3044\u307e\u3059\u3002\u4eca\u56de\u306fQA\u306e\u4ee3\u308f\u308a\u306b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3092\u7528\u3044\u307e\u3057\u305f\u3002","og_url":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/\u3010\u5b9f\u8df5\u7de8\u3011d-wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\/","og_site_name":"T-QARD Harbor","article_published_time":"2026-06-17T06:21:55+00:00","article_modified_time":"2026-06-17T06:27:45+00:00","og_image":[{"width":420,"height":301,"url":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-content\/uploads\/2026\/06\/e86a20425456acedcd5efa7cbfa66cb0.png","type":"image\/png"}],"author":"Moriaki Shimazaki","twitter_card":"summary_large_image","twitter_misc":{"\u57f7\u7b46\u8005":"Moriaki Shimazaki","\u63a8\u5b9a\u8aad\u307f\u53d6\u308a\u6642\u9593":"61\u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#article","isPartOf":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/"},"author":{"name":"Moriaki Shimazaki","@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/#\/schema\/person\/6adf10ecefe2a32c11ddbe87f4b69ff4"},"headline":"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2","datePublished":"2026-06-17T06:21:55+00:00","dateModified":"2026-06-17T06:27:45+00:00","mainEntityOfPage":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/"},"wordCount":604,"commentCount":0,"image":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#primaryimage"},"thumbnailUrl":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-content\/uploads\/2026\/06\/e86a20425456acedcd5efa7cbfa66cb0.png","keywords":["\u30ae\u30d6\u30b9\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0","\u30dc\u30eb\u30c4\u30de\u30f3\u6a5f\u68b0\u5b66\u7fd2","\u5236\u9650\u4ed8\u304d\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3","\u91cf\u5b50\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0"],"articleSection":["\u5b9f\u8df5\u8a18\u4e8b"],"inLanguage":"ja","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/","url":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/","name":"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2 - T-QARD Harbor","isPartOf":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/#website"},"primaryImageOfPage":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#primaryimage"},"image":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#primaryimage"},"thumbnailUrl":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-content\/uploads\/2026\/06\/e86a20425456acedcd5efa7cbfa66cb0.png","datePublished":"2026-06-17T06:21:55+00:00","dateModified":"2026-06-17T06:27:45+00:00","author":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/#\/schema\/person\/6adf10ecefe2a32c11ddbe87f4b69ff4"},"description":"\u89e3\u8aac\u8a18\u4e8b\u300cD-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2\u300d\u3067\u306fCD-1\u3067\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3068QA\u304b\u3089\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u5b66\u7fd2\u3055\u308c\u305fRBM\u3092\u4f7f\u3063\u3066\u3001BAS\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u5206\u985e\u3068\u753b\u50cf\u518d\u69cb\u6210\u304a\u3088\u3073\u5bfe\u6570\u5c24\u5ea6\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3059\u308b\u3068\u3044\u3046\u8ad6\u6587\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001\u5b9f\u969b\u306b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3001\u5143\u8ad6\u6587\u306e\u518d\u73fe\u5b9f\u9a13\u3092\u884c\u3044\u307e\u3059\u3002\u4eca\u56de\u306fQA\u306e\u4ee3\u308f\u308a\u306b\u30b7\u30df\u30e5\u30ec\u30fc\u30c6\u30c3\u30c9\u30fb\u30a2\u30cb\u30fc\u30ea\u30f3\u30b0(SA)\u3092\u7528\u3044\u307e\u3057\u305f\u3002","breadcrumb":{"@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#breadcrumb"},"inLanguage":"ja","potentialAction":[{"@type":"ReadAction","target":["https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/"]}]},{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#primaryimage","url":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-content\/uploads\/2026\/06\/e86a20425456acedcd5efa7cbfa66cb0.png","contentUrl":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-content\/uploads\/2026\/06\/e86a20425456acedcd5efa7cbfa66cb0.png","width":420,"height":301},{"@type":"BreadcrumbList","@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/2026\/06\/17\/%e3%80%90%e5%ae%9f%e8%b7%b5%e7%b7%a8%e3%80%91d-wave%e9%87%8f%e5%ad%90%e3%82%a2%e3%83%8b%e3%83%bc%e3%83%a9%e3%83%bc%e3%82%92%e7%94%a8%e3%81%84%e3%81%9f%e5%88%b6%e9%99%90%e3%83%9c%e3%83%ab%e3%83%84\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u30db\u30fc\u30e0","item":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/"},{"@type":"ListItem","position":2,"name":"\u3010\u5b9f\u8df5\u7de8\u3011D-Wave\u91cf\u5b50\u30a2\u30cb\u30fc\u30e9\u30fc\u3092\u7528\u3044\u305f\u5236\u9650\u30dc\u30eb\u30c4\u30de\u30f3\u30de\u30b7\u30f3\u306e\u5b66\u7fd2"}]},{"@type":"WebSite","@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/#website","url":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/","name":"T-QARD Harbor","description":"T-QARD Harbor\u306f\u6771\u5317\u5927\u5b66\u91cf\u5b50\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u7814\u7a76\u958b\u767a\u30bb\u30f3\u30bf\u30fc\u5b66\u751f\u30c1\u30fc\u30e0\u300cT-QARD Crews\u300d\u304c\u904b\u55b6\u3059\u308b\u3001 \u6570\u7406\u60c5\u5831\u7d71\u8a08\u3001\u91cf\u5b50\u60c5\u5831\u3001\u6700\u9069\u5316\u3001\u6a5f\u68b0\u5b66\u7fd2\u5206\u91ce\u306e\u60c5\u5831\u3092\u63d0\u4f9b\u3059\u308bWeb\u30b5\u30a4\u30c8\u3067\u3059","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ja"},{"@type":"Person","@id":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/#\/schema\/person\/6adf10ecefe2a32c11ddbe87f4b69ff4","name":"Moriaki Shimazaki","image":{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/secure.gravatar.com\/avatar\/ff04e3ac806c71c8384f4aba5b01894a7a3c6ab04904ae7fea5358b02cb15135?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/ff04e3ac806c71c8384f4aba5b01894a7a3c6ab04904ae7fea5358b02cb15135?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/ff04e3ac806c71c8384f4aba5b01894a7a3c6ab04904ae7fea5358b02cb15135?s=96&d=mm&r=g","caption":"Moriaki Shimazaki"},"description":"\u6771\u5317\u5927\u5b66 \u5de5\u5b66\u90e8 \u5b66\u58eb\u8ab2\u7a0b","url":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/author\/moriaki-shimazaki\/"}]}},"_links":{"self":[{"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/posts\/9070","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/users\/19"}],"replies":[{"embeddable":true,"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/comments?post=9070"}],"version-history":[{"count":7,"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/posts\/9070\/revisions"}],"predecessor-version":[{"id":9243,"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/posts\/9070\/revisions\/9243"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/media\/9247"}],"wp:attachment":[{"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/media?parent=9070"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/categories?post=9070"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/qard.is.tohoku.ac.jp\/T-Wave\/wp-json\/wp\/v2\/tags?post=9070"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}