{"id":477187,"date":"2023-08-09T09:08:44","date_gmt":"2023-08-09T09:08:44","guid":{"rendered":""},"modified":"2023-09-05T11:14:14","modified_gmt":"2023-09-05T11:14:14","slug":"fast-ai","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/jp\/wiki\/fast-ai\/","title":{"rendered":"\u9ad8\u901fAI"},"content":{"rendered":"<p>Fast AI \u306f\u3001AI \u3068\u6a5f\u68b0\u5b66\u7fd2 (ML) \u306e\u6c11\u4e3b\u5316\u3092\u76ee\u7684\u3068\u3057\u3066\u958b\u767a\u3055\u308c\u305f\u3001\u6700\u5148\u7aef\u306e\u9ad8\u52b9\u7387\u306a\u4eba\u5de5\u77e5\u80fd (AI) \u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u3002 Fast AI \u306f\u3001\u3053\u308c\u3089\u306e\u9ad8\u5ea6\u306a\u30c6\u30af\u30ce\u30ed\u30b8\u30fc\u3092\u3088\u308a\u30a2\u30af\u30bb\u30b9\u3057\u3084\u3059\u304f\u3001\u30e6\u30fc\u30b6\u30fc\u30d5\u30ec\u30f3\u30c9\u30ea\u30fc\u306b\u3059\u308b\u3053\u3068\u3067\u3001\u500b\u4eba\u3001\u7d44\u7e54\u3001\u7814\u7a76\u8005\u304c\u6df1\u3044\u6280\u8853\u7684\u5c02\u9580\u77e5\u8b58\u3092\u5fc5\u8981\u3068\u305b\u305a\u306b AI \u3068 ML \u306e\u529b\u3092\u6d3b\u7528\u3067\u304d\u308b\u3088\u3046\u306b\u3059\u308b\u3053\u3068\u3092\u76ee\u6307\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<h2>\u9ad8\u901f AI \u306e\u8d77\u6e90\u3068\u9032\u5316<\/h2>\n<p>Fast AI \u306f\u30012017 \u5e74\u306b Jeremy Howard \u3068 Rachel Thomas \u306b\u3088\u3063\u3066\u521d\u3081\u3066\u8a00\u53ca\u3055\u308c\u3001\u7d39\u4ecb\u3055\u308c\u307e\u3057\u305f\u3002AI \u3068\u30c7\u30fc\u30bf \u30b5\u30a4\u30a8\u30f3\u30b9\u306e\u5206\u91ce\u3067\u8457\u540d\u306a\u30cf\u30ef\u30fc\u30c9\u3068\u30c8\u30fc\u30de\u30b9\u306f\u3001AI \u306e\u6559\u80b2\u3068\u5b9f\u88c5\u3092\u3059\u3079\u3066\u306e\u4eba\u304c\u5229\u7528\u3067\u304d\u308b\u3088\u3046\u306b\u3059\u308b\u3068\u3044\u3046\u30d3\u30b8\u30e7\u30f3\u3092\u6301\u3063\u3066\u3044\u307e\u3057\u305f\u3002\u3053\u308c\u3092\u5ff5\u982d\u306b\u7f6e\u3044\u3066\u3001\u5f7c\u3089\u306f\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306e\u6a5f\u68b0\u5b66\u7fd2\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308b PyTorch \u4e0a\u306b\u69cb\u7bc9\u3055\u308c\u305f\u4f7f\u3044\u3084\u3059\u3044\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u3057\u3066 Fast AI \u3092\u8a2d\u8a08\u3057\u307e\u3057\u305f\u3002<\/p>\n<p>Fast AI \u306f\u3001\u305d\u306e\u30d1\u30ef\u30fc\u3068\u67d4\u8edf\u6027\u3092\u7dad\u6301\u3057\u306a\u304c\u3089\u3001PyTorch \u306b\u9ad8\u30ec\u30d9\u30eb\u3067\u4f7f\u3044\u3084\u3059\u3044\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u3092\u63d0\u4f9b\u3059\u308b\u3088\u3046\u306b\u8a2d\u8a08\u3055\u308c\u307e\u3057\u305f\u3002\u8a00\u3044\u63db\u3048\u308c\u3070\u3001Fast AI \u306f\u3001\u6a5f\u80fd\u3084\u5805\u7262\u6027\u3092\u640d\u306a\u3046\u3053\u3068\u306a\u304f\u3001\u9ad8\u5ea6\u306a ML \u30e2\u30c7\u30eb\u3068\u6280\u8853\u306e\u9069\u7528\u3092\u7c21\u7d20\u5316\u3059\u308b\u3053\u3068\u3092\u76ee\u7684\u3068\u3057\u3066\u3044\u307e\u3057\u305f\u3002<\/p>\n<h2>\u9ad8\u901f AI \u306e\u958b\u68b1: \u8a73\u7d30\u306a\u8abf\u67fb<\/h2>\n<p>Fast AI \u306f\u3001\u30c7\u30a3\u30fc\u30d7 \u30e9\u30fc\u30cb\u30f3\u30b0\u7528\u306e\u52d5\u7684\u3067\u67d4\u8edf\u306a\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002\u3053\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u306f\u3001\u3055\u307e\u3056\u307e\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3084\u624b\u6cd5\u3092\u4f7f\u7528\u3057\u3066\u8907\u96d1\u306a\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u304a\u3088\u3073\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u305f\u3081\u306e\u7c21\u7d20\u5316\u3055\u308c\u305f\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002\u305d\u306e\u4f7f\u3044\u3084\u3059\u3055\u3068\u3001\u6700\u5c0f\u9650\u306e\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3067\u6700\u5148\u7aef\u306e\u7d50\u679c\u3092\u751f\u6210\u3067\u304d\u308b\u6a5f\u80fd\u306b\u3088\u308a\u4eba\u6c17\u3092\u96c6\u3081\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>Fast AI \u306f\u3001\u753b\u50cf\u5206\u985e\u3001\u30c6\u30ad\u30b9\u30c8\u5206\u985e\u3001\u8868\u5f62\u5f0f\u30e2\u30c7\u30ea\u30f3\u30b0\u3001\u5354\u8abf\u30d5\u30a3\u30eb\u30bf\u30ea\u30f3\u30b0\u306a\u3069\u306e\u30bf\u30b9\u30af\u7528\u306e\u9ad8\u30ec\u30d9\u30eb API \u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u30c4\u30fc\u30eb\u3092\u4f7f\u7528\u3059\u308b\u3068\u3001\u30e6\u30fc\u30b6\u30fc\u306f\u308f\u305a\u304b\u6570\u884c\u306e\u30b3\u30fc\u30c9\u3067\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3001\u30c6\u30b9\u30c8\u3067\u304d\u307e\u3059\u3002\u3055\u3089\u306b\u3001Fast AI \u306f\u6a5f\u68b0\u5b66\u7fd2\u3068\u6df1\u5c64\u5b66\u7fd2\u306e\u30d9\u30b9\u30c8 \u30d7\u30e9\u30af\u30c6\u30a3\u30b9\u3092\u5b9f\u88c5\u3057\u3066\u304a\u308a\u3001\u30e6\u30fc\u30b6\u30fc\u304c\u3053\u308c\u3089\u306e\u6280\u8853\u3092\u52b9\u679c\u7684\u306b\u9069\u7528\u3059\u308b\u3053\u3068\u304c\u5bb9\u6613\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n<h2>\u9ad8\u901f AI \u306e\u5185\u90e8\u52d5\u4f5c<\/h2>\n<p>Fast AI \u306f\u3001\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\u3068\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u306e\u9ad8\u30ec\u30d9\u30eb\u3067\u30e6\u30fc\u30b6\u30fc\u30d5\u30ec\u30f3\u30c9\u30ea\u30fc\u306a API \u3092\u63d0\u4f9b\u3059\u308b\u3053\u3068\u3067\u3001\u8907\u96d1\u306a\u6df1\u5c64\u5b66\u7fd2\u30bf\u30b9\u30af\u3092\u7c21\u7d20\u5316\u3057\u307e\u3059\u3002 Fast AI \u306f\u5185\u90e8\u7684\u306b\u3001PyTorch \u306e\u5805\u7262\u304b\u3064\u67d4\u8edf\u306a\u6df1\u5c64\u5b66\u7fd2\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u4f7f\u7528\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>PyTorch \u306f\u3001\u30c6\u30f3\u30bd\u30eb\u3001\u30ec\u30a4\u30e4\u30fc\u3001\u640d\u5931\u95a2\u6570\u306a\u3069\u3001\u30cb\u30e5\u30fc\u30e9\u30eb \u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u4f5c\u6210\u3059\u308b\u305f\u3081\u306e\u57fa\u672c\u7684\u306a\u69cb\u6210\u8981\u7d20\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002\u3053\u308c\u306b\u52a0\u3048\u3066\u3001Fast AI \u306f\u3001\u6df1\u5c64\u5b66\u7fd2\u306b\u304a\u3051\u308b\u591a\u304f\u306e\u4e00\u822c\u7684\u306a\u30bf\u30b9\u30af\u3092\u7c21\u7d20\u5316\u3059\u308b\u62bd\u8c61\u5316\u30ec\u30a4\u30e4\u30fc\u3092\u8ffd\u52a0\u3057\u307e\u3059\u3002\u305f\u3068\u3048\u3070\u3001Fast AI \u306f\u3001\u30c7\u30fc\u30bf\u306e\u30ed\u30fc\u30c9\u3068\u62e1\u5f35\u3001\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\u3001\u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3068\u691c\u8a3c\u3001\u7d50\u679c\u306e\u5206\u6790\u306e\u305f\u3081\u306e\u4f7f\u3044\u3084\u3059\u3044\u6a5f\u80fd\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002<\/p>\n<p>Fast AI \u306f\u3001\u968e\u5c64\u5316\u3055\u308c\u305f API \u3068\u5b66\u7fd2\u7387\u30d5\u30a1\u30a4\u30f3\u30c0\u30fc\u3068\u3044\u3046 2 \u3064\u306e\u4e3b\u8981\u30b3\u30f3\u30dd\u30fc\u30cd\u30f3\u30c8\u3092\u901a\u3058\u3066\u3053\u306e\u6a5f\u80fd\u3092\u5b9f\u73fe\u3057\u307e\u3059\u3002\u968e\u5c64\u5316\u3055\u308c\u305f API \u306b\u3088\u308a\u3001\u30e6\u30fc\u30b6\u30fc\u306f\u30cb\u30fc\u30ba\u306b\u5fdc\u3058\u3066\u3055\u307e\u3056\u307e\u306a\u62bd\u8c61\u5316\u30ec\u30d9\u30eb\u3067\u4f5c\u696d\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002\u5b66\u7fd2\u7387\u30d5\u30a1\u30a4\u30f3\u30c0\u30fc\u306f\u3001\u30e6\u30fc\u30b6\u30fc\u304c\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u305f\u3081\u306e\u6700\u9069\u306a\u5b66\u7fd2\u7387\u3092\u9078\u629e\u3059\u308b\u306e\u306b\u5f79\u7acb\u3064\u30c4\u30fc\u30eb\u3067\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u304c\u5927\u5e45\u306b\u5411\u4e0a\u3057\u307e\u3059\u3002<\/p>\n<h2>Fast AI \u306e\u4e3b\u306a\u6a5f\u80fd<\/h2>\n<p>Fast AI \u306b\u306f\u3001\u6a5f\u68b0\u5b66\u7fd2\u30bf\u30b9\u30af\u3092\u5f37\u5316\u3059\u308b\u305f\u3081\u306b\u8a2d\u8a08\u3055\u308c\u305f\u4e00\u9023\u306e\u91cd\u8981\u306a\u6a5f\u80fd\u304c\u6e80\u8f09\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<ul>\n<li><strong>\u968e\u5c64\u5316\u3055\u308c\u305f API<\/strong>: \u30e6\u30fc\u30b6\u30fc\u304c\u597d\u307f\u306e\u62bd\u8c61\u5316\u30ec\u30d9\u30eb\u3092\u9078\u629e\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u3001\u3088\u308a\u9ad8\u3044\u67d4\u8edf\u6027\u3068\u5236\u5fa1\u304c\u63d0\u4f9b\u3055\u308c\u307e\u3059\u3002<\/li>\n<li><strong>\u5b66\u7fd2\u7387\u30d5\u30a1\u30a4\u30f3\u30c0\u30fc<\/strong>: \u6700\u9069\u306a\u5b66\u7fd2\u7387\u3092\u898b\u3064\u3051\u308b\u3053\u3068\u3067\u3001\u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0 \u30d7\u30ed\u30bb\u30b9\u3092\u6700\u9069\u5316\u3059\u308b\u306e\u306b\u5f79\u7acb\u3061\u307e\u3059\u3002<\/li>\n<li><strong>\u8ee2\u79fb\u5b66\u7fd2<\/strong>: \u30e6\u30fc\u30b6\u30fc\u306f\u4e8b\u524d\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3055\u308c\u305f\u30e2\u30c7\u30eb\u3092\u6d3b\u7528\u3057\u3066\u3001\u5c11\u306a\u3044\u30c7\u30fc\u30bf\u3068\u8a08\u7b97\u3067\u3088\u308a\u512a\u308c\u305f\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u9054\u6210\u3067\u304d\u307e\u3059\u3002<\/li>\n<li><strong>PyTorch \u3068\u306e\u7d71\u5408<\/strong>: PyTorch \u306e\u30d5\u30eb\u30d1\u30ef\u30fc\u3068\u67d4\u8edf\u6027\u3078\u306e\u30a2\u30af\u30bb\u30b9\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002<\/li>\n<li><strong>\u30d9\u30b9\u30c8\u30d7\u30e9\u30af\u30c6\u30a3\u30b9<\/strong>: \u6df1\u5c64\u5b66\u7fd2\u306e\u30d9\u30b9\u30c8 \u30d7\u30e9\u30af\u30c6\u30a3\u30b9\u3092\u5b9f\u88c5\u3057\u3001\u30e6\u30fc\u30b6\u30fc\u304c\u52b9\u679c\u7684\u306a\u30e2\u30c7\u30eb\u3092\u7c21\u5358\u306b\u69cb\u7bc9\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u307e\u3059\u3002<\/li>\n<\/ul>\n<h2>Fast AI \u306e\u7a2e\u985e: \u5206\u985e\u3068\u4f8b<\/h2>\n<p>Fast AI \u306f\u5358\u4e00\u306e\u7d71\u5408\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u304c\u3001\u3055\u307e\u3056\u307e\u306a\u7a2e\u985e\u306e\u30c7\u30fc\u30bf\u3084\u30bf\u30b9\u30af\u3092\u51e6\u7406\u3059\u308b\u305f\u3081\u306e\u4e00\u9023\u306e\u30c4\u30fc\u30eb\u3068\u6a5f\u80fd\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002\u6982\u8981\u306f\u6b21\u306e\u3068\u304a\u308a\u3067\u3059\u3002<\/p>\n<table>\n<thead>\n<tr>\n<th>\u30c7\u30fc\u30bf\u30fb\u30bf\u30a4\u30d7<\/th>\n<th>\u9ad8\u901fAI\u30e2\u30b8\u30e5\u30fc\u30eb<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u753b\u50cf<\/td>\n<td>\u30d3\u30b8\u30e7\u30f3<\/td>\n<\/tr>\n<tr>\n<td>\u6587\u7ae0<\/td>\n<td>\u6587\u7ae0<\/td>\n<\/tr>\n<tr>\n<td>\u8868\u5f62\u5f0f\u306e\u30c7\u30fc\u30bf<\/td>\n<td>\u8868\u5f62\u5f0f<\/td>\n<\/tr>\n<tr>\n<td>\u30ec\u30b3\u30e1\u30f3\u30c9\u30b7\u30b9\u30c6\u30e0\uff08\u5354\u8abf\u30d5\u30a3\u30eb\u30bf\u30ea\u30f3\u30b0\uff09<\/td>\n<td>\u30b3\u30e9\u30dc<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u5404\u30e2\u30b8\u30e5\u30fc\u30eb\u306f\u3001\u5bfe\u5fdc\u3059\u308b\u30bf\u30a4\u30d7\u306e\u30c7\u30fc\u30bf\u306b\u57fa\u3065\u3044\u3066\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3001\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u4e00\u9023\u306e\u9ad8\u30ec\u30d9\u30eb\u95a2\u6570\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002<\/p>\n<h2>Fast AI\u6d3b\u7528\u306e\u8ab2\u984c\u3068\u89e3\u6c7a\u7b56<\/h2>\n<p>Fast AI \u306f\u3001\u5b66\u8853\u3084\u7814\u7a76\u304b\u3089\u30d8\u30eb\u30b9\u30b1\u30a2\u3001\u96fb\u5b50\u5546\u53d6\u5f15\u3001\u81ea\u52d5\u904b\u8ee2\u8eca\u306a\u3069\u306e\u696d\u754c\u306b\u81f3\u308b\u307e\u3067\u3001\u5e45\u5e83\u304f\u5fdc\u7528\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u305f\u3060\u3057\u3001\u4ed6\u306e\u30c4\u30fc\u30eb\u3068\u540c\u69d8\u306b\u3001\u8ab2\u984c\u304c\u751f\u3058\u308b\u53ef\u80fd\u6027\u304c\u3042\u308a\u307e\u3059\u3002\u305f\u3068\u3048\u3070\u3001\u9ad8\u30ec\u30d9\u30eb API \u306f\u591a\u304f\u306e\u30bf\u30b9\u30af\u3092\u7c21\u7d20\u5316\u3057\u307e\u3059\u304c\u3001\u62bd\u8c61\u5316\u306e\u30ec\u30d9\u30eb\u304c\u539f\u56e0\u3067\u30e2\u30c7\u30eb\u306e\u30ab\u30b9\u30bf\u30de\u30a4\u30ba\u3084\u30c7\u30d0\u30c3\u30b0\u304c\u56f0\u96e3\u306b\u306a\u308b\u5834\u5408\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n<p>\u3053\u306e\u554f\u984c\u306b\u5bfe\u3059\u308b\u89e3\u6c7a\u7b56\u306e 1 \u3064\u306f\u3001\u30e6\u30fc\u30b6\u30fc\u304c\u62bd\u8c61\u5316\u30ec\u30d9\u30eb\u3092\u9078\u629e\u3067\u304d\u308b\u968e\u5c64\u578b API \u3067\u3059\u3002\u3088\u308a\u5358\u7d14\u306a\u30bf\u30b9\u30af\u306e\u5834\u5408\u306f\u9ad8\u30ec\u30d9\u30eb API \u3092\u4f7f\u7528\u3067\u304d\u307e\u3059\u304c\u3001\u30ab\u30b9\u30bf\u30de\u30a4\u30ba\u304c\u5fc5\u8981\u306a\u3088\u308a\u8907\u96d1\u306a\u30bf\u30b9\u30af\u306e\u5834\u5408\u306f\u3001\u30e6\u30fc\u30b6\u30fc\u306f\u4f4e\u30ec\u30d9\u30eb API \u3092\u4ecb\u3057\u3066 PyTorch \u3092\u76f4\u63a5\u64cd\u4f5c\u3067\u304d\u307e\u3059\u3002<\/p>\n<h2>\u6bd4\u8f03\u3068\u7279\u5fb4: \u9ad8\u901f AI \u3068\u4ed6\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af<\/h2>\n<p>Fast AI\u3001TensorFlow\u3001Keras \u306f\u3059\u3079\u3066\u3001\u30c7\u30a3\u30fc\u30d7 \u30e9\u30fc\u30cb\u30f3\u30b0\u7528\u306e\u5f37\u529b\u306a\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u3002\u305f\u3060\u3057\u3001\u305d\u308c\u305e\u308c\u306b\u9577\u6240\u3068\u77ed\u6240\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n<table>\n<thead>\n<tr>\n<th>\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af<\/th>\n<th>\u4f7f\u3044\u3084\u3059\u3055<\/th>\n<th>\u67d4\u8edf\u6027<\/th>\n<th>\u5b66\u7fd2\u66f2\u7dda<\/th>\n<th>\u4e8b\u524d\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3055\u308c\u305f\u30e2\u30c7\u30eb<\/th>\n<th>\u6700\u9069\u306a\u7528\u9014<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u9ad8\u901fAI<\/td>\n<td>\u9ad8\u3044<\/td>\n<td>\u9ad8\u3044<\/td>\n<td>\u4f4e\u3044<\/td>\n<td>\u591a\u304f\u306e<\/td>\n<td>\u521d\u5fc3\u8005\u3068\u4e0a\u7d1a\u30e6\u30fc\u30b6\u30fc<\/td>\n<\/tr>\n<tr>\n<td>TensorFlow<\/td>\n<td>\u4e2d\u304f\u3089\u3044<\/td>\n<td>\u9ad8\u3044<\/td>\n<td>\u9ad8\u3044<\/td>\n<td>\u591a\u304f\u306e<\/td>\n<td>\u4e0a\u7d1a\u30e6\u30fc\u30b6\u30fc<\/td>\n<\/tr>\n<tr>\n<td>\u30b1\u30e9\u30b9<\/td>\n<td>\u9ad8\u3044<\/td>\n<td>\u4e2d\u304f\u3089\u3044<\/td>\n<td>\u4f4e\u3044<\/td>\n<td>\u5c11\u3057<\/td>\n<td>\u521d\u5fc3\u8005\u5411\u3051<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>TensorFlow \u306f\u512a\u308c\u305f\u67d4\u8edf\u6027\u3092\u63d0\u4f9b\u3057\u307e\u3059\u304c\u3001\u5b66\u7fd2\u66f2\u7dda\u306f\u3088\u308a\u6025\u306b\u306a\u308a\u307e\u3059\u3002 Keras \u306f\u30e6\u30fc\u30b6\u30fc\u30d5\u30ec\u30f3\u30c9\u30ea\u30fc\u3067\u3059\u304c\u3001\u3042\u307e\u308a\u5236\u5fa1\u3067\u304d\u307e\u305b\u3093\u3002\u9ad8\u901f AI \u306f\u4f7f\u3044\u3084\u3059\u3055\u3068\u67d4\u8edf\u6027\u306e\u30d0\u30e9\u30f3\u30b9\u304c\u53d6\u308c\u3066\u304a\u308a\u3001\u521d\u5fc3\u8005\u3068\u4e0a\u7d1a\u30e6\u30fc\u30b6\u30fc\u306e\u4e21\u65b9\u306b\u9069\u3057\u305f\u9078\u629e\u80a2\u3068\u306a\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n<h2>\u5c06\u6765\u306e\u5c55\u671b: \u9ad8\u901f AI \u3068\u65b0\u8208\u30c6\u30af\u30ce\u30ed\u30b8\u30fc<\/h2>\n<p>\u9ad8\u901f AI \u306f\u3001\u4eba\u5de5\u77e5\u80fd\u306e\u5206\u91ce\u81ea\u4f53\u3068\u540c\u69d8\u306b\u3001\u7d99\u7d9a\u7684\u306b\u9032\u5316\u3057\u3066\u3044\u307e\u3059\u3002\u30d5\u30a7\u30c7\u30ec\u30fc\u30c6\u30c3\u30c9 \u30e9\u30fc\u30cb\u30f3\u30b0\u3001\u81ea\u52d5\u6a5f\u68b0\u5b66\u7fd2\u3001\u91cf\u5b50\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u306a\u3069\u306e\u65b0\u8208\u30c6\u30af\u30ce\u30ed\u30b8\u30fc\u306f\u3001AI \u306e\u72b6\u6cc1\u306b\u9769\u547d\u3092\u8d77\u3053\u305d\u3046\u3068\u3057\u3066\u3044\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u30c6\u30af\u30ce\u30ed\u30b8\u30fc\u304c\u6210\u719f\u3059\u308b\u306b\u3064\u308c\u3066\u3001Fast AI \u306b\u3082\u3053\u308c\u3089\u306e\u9032\u6b69\u304c\u7d44\u307f\u8fbc\u307e\u308c\u3001\u6d17\u7df4\u3055\u308c\u305f AI \u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\u3068\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u306e\u30d7\u30ed\u30bb\u30b9\u304c\u3055\u3089\u306b\u7c21\u7d20\u5316\u3055\u308c\u308b\u3053\u3068\u304c\u671f\u5f85\u3067\u304d\u307e\u3059\u3002<\/p>\n<h2>\u9ad8\u901f AI \u3068\u30d7\u30ed\u30ad\u30b7 \u30b5\u30fc\u30d0\u30fc: \u672a\u77e5\u306e\u76f8\u4e57\u52b9\u679c<\/h2>\n<p>\u30d7\u30ed\u30ad\u30b7 \u30b5\u30fc\u30d0\u30fc\u306f\u30af\u30e9\u30a4\u30a2\u30f3\u30c8\u3068\u30b5\u30fc\u30d0\u30fc\u306e\u9593\u306e\u4ef2\u4ecb\u8005\u3068\u3057\u3066\u6a5f\u80fd\u3057\u3001\u30c7\u30fc\u30bf \u30ad\u30e3\u30c3\u30b7\u30e5\u3001Web \u30d5\u30a3\u30eb\u30bf\u30ea\u30f3\u30b0\u3001IP \u30de\u30b9\u30ad\u30f3\u30b0\u306a\u3069\u306e\u3055\u307e\u3056\u307e\u306a\u6a5f\u80fd\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002\u4e00\u898b\u3059\u308b\u3068\u3001Fast AI \u3068\u30d7\u30ed\u30ad\u30b7 \u30b5\u30fc\u30d0\u30fc\u306e\u9593\u306b\u76f4\u63a5\u306e\u76f8\u95a2\u95a2\u4fc2\u304c\u306a\u3044\u3088\u3046\u306b\u898b\u3048\u307e\u3059\u304c\u3001\u6f5c\u5728\u7684\u306a\u30e6\u30fc\u30b9\u30b1\u30fc\u30b9\u304c\u5b58\u5728\u3059\u308b\u53ef\u80fd\u6027\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n<p>\u305d\u306e\u3088\u3046\u306a\u30e6\u30fc\u30b9\u30b1\u30fc\u30b9\u306e 1 \u3064\u306f\u3001\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u306e\u30c7\u30fc\u30bf\u53d6\u5f97\u3067\u3059\u3002\u30d7\u30ed\u30ad\u30b7 \u30b5\u30fc\u30d0\u30fc\u3092\u4f7f\u7528\u3059\u308b\u3068\u3001\u5730\u7406\u7684\u306b\u5236\u9650\u3055\u308c\u305f\u30c7\u30fc\u30bf\u3078\u306e\u30a2\u30af\u30bb\u30b9\u304c\u5bb9\u6613\u306b\u306a\u308a\u3001\u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u306b\u4f7f\u7528\u3067\u304d\u307e\u3059\u3002\u3053\u308c\u306f\u3001\u5834\u6240\u56fa\u6709\u306e\u60c5\u5831\u3092\u5fc5\u8981\u3068\u3059\u308b\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3059\u308b\u5834\u5408\u306b\u7279\u306b\u5f79\u7acb\u3061\u307e\u3059\u3002<\/p>\n<h2>\u95a2\u9023\u30ea\u30f3\u30af<\/h2>\n<ul>\n<li><a href=\"https:\/\/www.fast.ai\/\" target=\"_new\" rel=\"noopener nofollow\">Fast AI\u306e\u516c\u5f0f\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/fastai\" target=\"_new\" rel=\"noopener nofollow\">\u9ad8\u901f AI GitHub \u30ea\u30dd\u30b8\u30c8\u30ea<\/a><\/li>\n<li><a href=\"https:\/\/course.fast.ai\/\" target=\"_new\" rel=\"noopener nofollow\">\u9ad8\u901f AI \u30b3\u30fc\u30b9<\/a><\/li>\n<li><a href=\"https:\/\/pytorch.org\/\" target=\"_new\" rel=\"noopener nofollow\">PyTorch \u516c\u5f0f\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8<\/a><\/li>\n<\/ul>\n<p>Fast AI \u306f\u3001\u30c7\u30a3\u30fc\u30d7 \u30e9\u30fc\u30cb\u30f3\u30b0\u7528\u306e\u5f37\u529b\u304b\u3064\u67d4\u8edf\u3067\u4f7f\u3044\u3084\u3059\u3044\u30c4\u30fc\u30eb\u3092\u63d0\u4f9b\u3057\u3001\u521d\u5fc3\u8005\u306b\u3082\u5c02\u9580\u5bb6\u306b\u3082 AI \u306e\u4e16\u754c\u3078\u306e\u6249\u3092\u958b\u304d\u307e\u3059\u3002\u7d99\u7d9a\u7684\u306a\u9032\u5316\u3068\u6210\u9577\u3092\u7d9a\u3051\u308b AI \u5206\u91ce\u306b\u3088\u308a\u3001Fast AI \u306f\u9593\u9055\u3044\u306a\u304f\u4eca\u5f8c\u6570\u5e74\u9593\u6ce8\u76ee\u3055\u308c\u308b\u30c4\u30fc\u30eb\u3067\u3059\u3002<\/p>","protected":false},"featured_media":468374,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-477187","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Fast AI: An Introduction to Speed and Intelligence in Computing<\/mark>","faq_items":[{"question":"What is Fast AI?","answer":"<p>Fast AI is a high-efficiency, user-friendly artificial intelligence (AI) framework aimed at democratizing AI and machine learning. It simplifies the process of building and training advanced machine learning models without the need for deep technical expertise.<\/p>"},{"question":"Who developed Fast AI and when was it first introduced?","answer":"<p>Fast AI was developed and introduced by Jeremy Howard and Rachel Thomas in 2017. Both are recognized figures in the field of AI and data science and they created Fast AI with the vision of making AI education and implementation accessible to everyone.<\/p>"},{"question":"How does Fast AI work?","answer":"<p>Fast AI provides a simplified interface for building and training complex machine learning models using various algorithms and techniques. It uses PyTorch's robust and flexible deep learning framework internally. It adds a layer of abstraction that simplifies many common tasks in deep learning such as loading and augmenting data, constructing models, training and validating models, and analyzing results.<\/p>"},{"question":"What are the key features of Fast AI?","answer":"<p>The key features of Fast AI include a Layered API for choosing the level of abstraction, a Learning rate finder for optimizing the model training process, Transfer learning capabilities to leverage pre-trained models, Integration with PyTorch for added flexibility and power, and the implementation of best practices for deep learning.<\/p>"},{"question":"What types of Fast AI exist?","answer":"<p>Fast AI provides a suite of tools and capabilities for handling various types of data and tasks. It offers modules for different types of data including images (vision), text (text), tabular data (tabular), and collaborative filtering for recommendation systems (collab).<\/p>"},{"question":"What are some problems and solutions related to using Fast AI?","answer":"<p>While Fast AI's high-level API simplifies many tasks, it can sometimes be difficult to customize or debug models due to the level of abstraction. The layered API of Fast AI, which allows users to choose their level of abstraction, provides a solution to this problem.<\/p>"},{"question":"How does Fast AI compare with similar frameworks like TensorFlow and Keras?","answer":"<p>While all three are powerful frameworks, Fast AI strikes a balance between ease of use and flexibility, making it suitable for both beginners and advanced users. TensorFlow offers great flexibility but has a steeper learning curve, while Keras is user-friendly but offers less control.<\/p>"},{"question":"What are the future prospects related to Fast AI?","answer":"<p>Fast AI, like AI itself, is continually evolving. Emerging technologies like federated learning, automated machine learning, and quantum computing are expected to revolutionize AI, and Fast AI is likely to incorporate these advancements in the future.<\/p>"},{"question":"How can proxy servers be used with Fast AI?","answer":"<p>Proxy servers, which act as intermediaries between clients and servers, can facilitate access to geo-restricted data for training machine learning models in Fast AI. This can be particularly useful when building models that require location-specific information.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/jp\/wp-json\/wp\/v2\/wiki\/477187","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/jp\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/jp\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/jp\/wp-json\/wp\/v2\/wiki\/477187\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/jp\/wp-json\/wp\/v2\/media\/468374"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/jp\/wp-json\/wp\/v2\/media?parent=477187"}],"curies":[{"name":"\u3046\u30fc\u3093","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}