{"id":11736,"date":"2019-09-27T20:21:36","date_gmt":"2019-09-27T11:21:36","guid":{"rendered":"https:\/\/deeplearning.jp\/?page_id=11736"},"modified":"2019-10-29T19:51:20","modified_gmt":"2019-10-29T10:51:20","slug":"dl4us_3rd","status":"publish","type":"page","link":"https:\/\/deeplearning.jp\/en\/lectures\/dl4us_3rd\/","title":{"rendered":"(\u65e5\u672c\u8a9e) Deep Learning\u5b9f\u8df5\u958b\u767a\u8b1b\u5ea7\uff08DL4US\uff09 \u7b2c3\u671f"},"content":{"rendered":"

Sorry, this entry is only available in \u65e5\u672c\u8a9e<\/a>. For the sake of viewer convenience, the content is shown below in the alternative language. You may click the link to switch the active language.<\/p>

<\/div><\/div><\/div>
\n
<\/div>\n\n

\u8b1b\u5ea7\u6982\u8981<\/h2>\n

 <\/p>\n

Deep Learning\u5b9f\u8df5\u958b\u767a\u8b1b\u5ea7\u300cDL4US\u300d\u306f\u3001\u6771\u4eac\u5927\u5b66\u677e\u5c3e\u7814\u7a76\u5ba4\u304c\u958b\u50ac\u3059\u308b\u3001Deep Learning\u306e\u5b9f\u52d9\u3067\u306e\u6d3b\u7528\u3092\u8003\u3048\u308b\u958b\u767a\u8005\u3092\u5bfe\u8c61\u3068\u3057\u305f\u3001\u7121\u511f\u30aa\u30f3\u30e9\u30a4\u30f3\u6559\u80b2\u30d7\u30ed\u30b0\u30e9\u30e0\u3067\u3059\u30022018\u5e74\u304b\u3089\u30b9\u30bf\u30fc\u30c8\u3057\u3001\u7b2c1\u671f\u30fb\u7b2c2\u671f\u5408\u308f\u305b\u3066500\u540d\u4ee5\u4e0a\u306e\u65b9\u306b\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u63d0\u4f9b\u3057\u3066\u3044\u307e\u3059\u3002\u307e\u305f\u3001\u672c\u5e74\u3088\u308a\u958b\u767a\u3057\u305f\u6f14\u7fd2\u30b3\u30f3\u30c6\u30f3\u30c4\u306e\u4e00\u822c\u516c\u958b<\/a>\u3092\u884c\u306a\u3044\u3001\u3088\u308a\u591a\u304f\u306e\u65b9\u306bDeep Learning\u6280\u8853\u7fd2\u5f97\u306e\u6a5f\u4f1a\u3092\u63d0\u4f9b\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n

\u7b2c3\u671f\u3067\u306f\u3001”\u53d7\u8b1b\u751f\u30b3\u30df\u30e5\u30cb\u30c6\u30a3” \u306e\u4fa1\u5024\u6700\u5927\u5316\u3092\u76ee\u6307\u3057\u3066\u30011\uff09\u30b3\u30f3\u30da\u5f62\u5f0f\u306e\u8ab2\u984c\u3092\u901a\u3058\u305f\u7af6\u4e89\u30012\uff09\u53d7\u8b1b\u751f\u30d5\u30a9\u30fc\u30e9\u30e0\u3067\u306e\u8b70\u8ad6\u30fb\u52a9\u3051\u5408\u3044\u30013\uff09\u8b1b\u5ea7\u671f\u9593\u4e2d\u30fb\u5f8c\u306e\u4ea4\u6d41\u3001\u306b\u91cd\u70b9\u3092\u7f6e\u3044\u305f\u904b\u55b6\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n

\u5b9f\u8df5\u7684\u306aDeep Learning\u6280\u8853\u3092\u8eab\u306b\u4ed8\u3051\u305f\u3044\u65b9\u306e\u3054\u5fdc\u52df\u3092\u304a\u5f85\u3061\u3057\u3066\u304a\u308a\u307e\u3059\u3002<\/p>\n<\/div><\/div>\n \n\n \n Apply <\/a>\n \n\n\n <\/div>\n\n\n\n\n

\uff08\u30ea\u30f3\u30af\u5148\u306e\u6ce8\u610f\u4e8b\u9805\u3092\u3088\u304f\u8aad\u3093\u3067\u767b\u9332\u304f\u3060\u3055\u3044\uff09<\/p>\n<\/div><\/div>\n

<\/div>\n\n

\u8b1b\u5ea7\u306e\u7279\u5fb4<\/h2>\n<\/div><\/div>

\u6f14\u7fd2\u30b3\u30f3\u30c6\u30f3\u30c4\u306f\u4ee5\u4e0b\u306e\u30da\u30fc\u30b8\u306b\u3066\u516c\u958b\u3057\u3066\u304a\u308a\u3001\u500b\u4eba\u3067\u306e\u5229\u7528\u306b\u9650\u308a\u3001\u81ea\u7531\u306b\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u53ef\u80fd\u3067\u3059\u3002<\/p>\n

\u516c\u958b\u30da\u30fc\u30b8<\/a><\/p>\n<\/div><\/div>

\"\"<\/div>\n

1\u53d7\u8b1b\u8005 \u2013 1GPU\u30b5\u30fc\u30d0<\/h4>\n

\u5168\u3066\u306e\u53d7\u8b1b\u8005\u306b\u4e00\u4eba\u4e00\u53f0\u306e\u72ec\u7acb\u3057\u305f\u4eee\u60f3GPU\u30b5\u30fc\u30d0\u304c\u5272\u308a\u5f53\u3066\u3089\u308c\u307e\u3059\uff0e\u53d7\u8b1b\u4e2d\u306f\u4ed6\u306e\u53d7\u8b1b\u8005\u306e\u5f71\u97ff\u3092\u53d7\u3051\u308b\u3053\u3068\u306a\u304f\u5b66\u7fd2\u3092\u9032\u3081\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/div><\/div><\/div><\/div><\/div>

\"\"<\/div>\n

\u30d6\u30e9\u30a6\u30b6\u306e\u307f\u5fc5\u8981<\/h4>\n

\u5fc5\u8981\u306a\u3082\u306e\u306fWeb\u30d6\u30e9\u30a6\u30b6\u306e\u307f\u3067\u3059\u3002\u30d6\u30e9\u30a6\u30b6\u3092\u901a\u3058\u3066GPU\u3092\u5229\u7528\u3057\u305fPython\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u304c\u53ef\u80fd\u306a\u958b\u767a\u74b0\u5883\u304c\u63d0\u4f9b\u3055\u308c\u307e\u3059\u3002\u30af\u30ea\u30c3\u30af\u64cd\u4f5c\u306e\u307f\u3067\u6f14\u7fd2\u3092\u958b\u59cb\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/div><\/div><\/div><\/div><\/div>

\"\"<\/div>\n

\u69cb\u7bc9\u6e08\u307f\u74b0\u5883<\/h4>\n

\u5fc5\u8981\u306a\u5168\u3066\u306eDeep Learning\u30fb\u6a5f\u68b0\u5b66\u7fd2\u30e9\u30a4\u30d6\u30e9\u30ea\u304c\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3055\u308c\u3001\u69cb\u7bc9\u6e08\u307f\u306e\u74b0\u5883\u304c\u914d\u5e03\u3055\u308c\u307e\u3059\u306e\u3067\u3001\u3059\u3050\u306b\u5b66\u7fd2\u3092\u958b\u59cb\u3057\u672c\u984c\u306b\u96c6\u4e2d\u3057\u3066\u53d6\u308a\u7d44\u3080\u3053\u3068\u304c\u53ef\u80fd\u3067\u3059\u3002<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div>

\"\"<\/div>\n

\u6f14\u7fd2\u4e2d\u5fc3\u3067\u52b9\u7387\u826f\u304f\u77ed\u671f\u7fd2\u5f97<\/h4>\n

\u672c\u30d7\u30ed\u30b0\u30e9\u30e0\u306e\u6700\u5927\u306e\u7279\u5fb4\u306e\u4e00\u3064\u306f\u3001\u5168\u3066\u306e\u30c8\u30d4\u30c3\u30af\u306b\u3064\u3044\u3066\uff0c\u6f14\u7fd2\u3092\u4e2d\u5fc3\u306b\u69cb\u6210\u3055\u308c\u3066\u3044\u308b\u70b9\u3067\u3059\u3002\u5b9f\u969b\u306b\u624b\u3092\u52d5\u304b\u3057\u306a\u304c\u3089\u7406\u89e3\u3092\u9032\u3081\u308b\u3053\u3068\u3067\u3001\u52b9\u7387\u3088\u304f\u5b66\u7fd2\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/div><\/div><\/div><\/div><\/div>

\"\"<\/div>\n

\u30e2\u30c7\u30eb\u306e\u5b66\u7fd2<\/h4>\n

Deep Learning\u6280\u8853\u3067\u306f\u3001\u30e2\u30c7\u30eb\u304c\u5b66\u7fd2\u3059\u308b\u69d8\u5b50\u3092\u89b3\u6e2c\u3057\u306a\u304c\u3089\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u8abf\u6574\u3059\u308b\u3053\u3068\u3067\u3001\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u5fdc\u3058\u305f\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306e\u6700\u5927\u5316\u3092\u56f3\u308b\u3053\u3068\u304c\u975e\u5e38\u306b\u91cd\u8981\u3067\u3059\u3002\u3053\u306e\u4e00\u9023\u306e\u6d41\u308c\u3092\u5168\u3066\u306e\u6f14\u7fd2\u3067\u7d4c\u9a13\u3059\u308b\u3053\u3068\u3067\u3001\u91cd\u8981\u306a\u8981\u7d20\u3092\u8eab\u306b\u3064\u3051\u3089\u308c\u307e\u3059\u3002<\/p>\n<\/div><\/div><\/div><\/div><\/div>

\"\"<\/div>\n

Keras\u306e\u307f<\/h4>\n

\u30b3\u30f3\u30c6\u30f3\u30c4\u5185\u306e\u30b3\u30fc\u30c9\u306f\u5168\u3066Keras\u3068\u6a19\u6e96\u7684\u306a\u30e9\u30a4\u30d6\u30e9\u30ea\uff08Numpy, Scipy, Scikit-learn\u7b49\uff09\u3067\u69cb\u6210\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div>

<\/div><\/div><\/div><\/div>
<\/div><\/div><\/div>
\n
<\/div>\n\n

\u4f01\u753b\u30fb\u904b\u55b6<\/h2>\n<\/div><\/div>
\n
\n \n
\n\n
\n\n\n
\n
\n \"\" <\/div>\n <\/div>\n \n\n\n
\n\n
\n

\n <\/h3>\n <\/div>\n\n
\n

\n \u677e\u5c3e\u8c4a <\/h4>\n <\/div>\n\n
\n
\n \u6771\u4eac\u5927\u5b66\u5927\u5b66\u9662\u5de5\u5b66\u7cfb\u7814\u7a76\u79d1 <\/div>\n <\/div>\n\n \n <\/div>\n \n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n\n <\/div><\/div><\/div>
\n
\n \n
\n\n
\n\n\n
\n
\n \"\" <\/div>\n <\/div>\n \n\n\n
\n\n
\n

\n <\/h3>\n <\/div>\n\n
\n

\n \u9234\u6728\u96c5\u5927 <\/h4>\n <\/div>\n\n
\n
\n \u6771\u4eac\u5927\u5b66\u5927\u5b66\u9662\u5de5\u5b66\u7cfb\u7814\u7a76\u79d1 <\/div>\n <\/div>\n\n \n <\/div>\n \n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n\n <\/div><\/div><\/div>
\n
\n \n
\n\n
\n\n\n
\n
\n \"\" <\/div>\n <\/div>\n \n\n\n
\n\n
\n

\n <\/h3>\n <\/div>\n\n
\n

\n \u4f50\u3005\u6728 \u512a <\/h4>\n <\/div>\n\n
\n
\n \u6771\u4eac\u5927\u5b66\u5927\u5b66\u9662\u5de5\u5b66\u7cfb\u7814\u7a76\u79d1 <\/div>\n <\/div>\n\n \n <\/div>\n \n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n\n <\/div><\/div><\/div><\/div>\n
<\/div>\n\n

\u30b9\u30bf\u30c3\u30d5<\/h2>\n<\/div><\/div>\n
<\/div>\n\n
\n
\n \n
\n\n
\n\n\n
\n
\n \"\" <\/div>\n <\/div>\n \n\n\n
\n\n
\n

\n <\/h3>\n <\/div>\n\n
\n

\n \u85e4\u91ce \u66a2 <\/h4>\n <\/div>\n\n
\n
\n \u6771\u4eac\u5927\u5b66\u5927\u5b66\u9662\u65b0\u9818\u57df\u5275\u6210\u79d1\u5b66\u7814\u7a76\u79d1 <\/div>\n <\/div>\n\n \n <\/div>\n \n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n\n <\/div><\/div><\/div>
\n
\n \n
\n\n
\n\n\n
\n
\n \"\" <\/div>\n <\/div>\n \n\n\n
\n\n
\n

\n <\/h3>\n <\/div>\n\n
\n

\n \u77f3\u4e0a \u4eae\u4ecb <\/h4>\n <\/div>\n\n
\n
\n \u6771\u4eac\u5927\u5b66\u5927\u5b66\u9662\u7406\u5b66\u7cfb\u7814\u7a76\u79d1 <\/div>\n <\/div>\n\n \n <\/div>\n \n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n\n <\/div><\/div><\/div>
\n
\n \n
\n\n
\n\n\n
\n
\n \"\" <\/div>\n <\/div>\n \n\n\n
\n\n
\n

\n <\/h3>\n <\/div>\n\n
\n

\n \u4e45\u4fdd \u9759\u771f <\/h4>\n <\/div>\n\n
\n
\n \u6771\u4eac\u5927\u5b66\u5927\u5b66\u9662\u5de5\u5b66\u7cfb\u7814\u7a76\u79d1 <\/div>\n <\/div>\n\n \n <\/div>\n \n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n <\/div>\n \n\n <\/div><\/div><\/div><\/div><\/div><\/div><\/div>
<\/div><\/div><\/div><\/div>
\n
<\/div>\n\n

\u8b1b\u5ea7\u5185\u5bb9<\/h2>\n<\/div><\/div><\/div><\/div><\/div><\/div>
<\/div><\/div><\/div>
<\/p>\n\n\n\n\n\n\n\n\n\n\n\n
Lesson0:
\n\u6a5f\u68b0\u5b66\u7fd2\u30fbDeep Learning\u306e\u30ad\u30bd<\/th>\n		\u6a5f\u68b0\u5b66\u7fd2\u6982\u89b3<\/td>\n<\/tr>\n
Lesson1:
\n\u624b\u66f8\u304d\u6587\u5b57\u8a8d\u8b58\u3092\u3057\u3088\u3046<\/th>\n		Keras\u5165\u9580\u3001MNIST\u3001MLP\u3001\u524d\u51e6\u7406\u3001\u52fe\u914d\u306b\u95a2\u3059\u308b\u30c6\u30af\u30cb\u30c3\u30af\u3001\u904e\u5b66\u7fd2\u306b\u95a2\u3059\u308b\u624b\u6cd5\u3001Fashion MNIST<\/td>\n<\/tr>\n
Lesson2:
\n\u7573\u307f\u8fbc\u307f\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af<\/th>\n		CNN\u57fa\u790e\u3001Data Augmentation\u3001\u753b\u50cf\u30c7\u30fc\u30bf\u306e\u6b63\u898f\u5316\u3001Batch Normalization\u3001Skip Connection<\/td>\n<\/tr>\n
Lesson3:
\n\u7cfb\u5217\u30c7\u30fc\u30bf\u3067\u4e88\u6e2c\u3055\u305b\u3066\u307f\u3088\u3046<\/th>\n		RNN\u3001BPTT\u3001Gradient Clipping\u3001LSTM\u3001GRU<\/td>\n<\/tr>\n
Lesson4:
\n\u30cb\u30e5\u30fc\u30e9\u30eb\u7ffb\u8a33\u30e2\u30c7\u30eb\u3092\u3064\u304f\u3063\u3066\u307f\u3088\u3046<\/th>\n		\u8a00\u8a9e\u30e2\u30c7\u30eb\u3001\u5206\u6563\u8868\u73fe\u3001Seq2Seq\u3001Keras Functional API\u3001Attention<\/td>\n<\/tr>\n
Lesson5:
\n\u753b\u50cf\u304b\u3089\u30ad\u30e3\u30d7\u30b7\u30e7\u30f3\u3092\u751f\u6210\u3057\u3088\u3046<\/th>\n		MSCOCO\u3001\u5b66\u7fd2\u6e08\u307f\u30e2\u30c7\u30eb\u306e\u5229\u7528\u3001\u30ad\u30e3\u30d7\u30b7\u30e7\u30f3\u751f\u6210\u3001Attention<\/td>\n<\/tr>\n
Lesson6:
\n\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u306b\u753b\u50cf\u3092\u751f\u6210\u3055\u305b\u3088\u3046<\/th>\n		\u751f\u6210\u30e2\u30c7\u30eb\u5165\u9580\u3001GAN\u3001Conditional GAN\u3001VAE<\/td>\n<\/tr>\n
Lesson7:
\n\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u3067\u30b2\u30fc\u30e0\u3092\u653b\u7565\u3059\u308bAI\u3092\u3064\u304f\u308d\u3046<\/th>\n		\u5f37\u5316\u5b66\u7fd2\u5165\u9580\u3001Q\u5b66\u7fd2\u3001DQN\u3001OpenAI Gym\u3001Double DQN\u3001Dueling Network<\/td>\n<\/tr>\n
\u6700\u7d42\u8ab2\u984c:<\/th>\nTBD<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\u203b \u5185\u5bb9\u306b\u95a2\u3057\u3066\u306f\u3001\u5909\u66f4\u3068\u306a\u308b\u53ef\u80fd\u6027\u304c\u3054\u3056\u3044\u307e\u3059\u3002\u3054\u4e86\u627f\u4e0b\u3055\u3044\u3002<\/p>\n<\/div><\/div>\n

<\/div>\n\n <\/div><\/div><\/div>
<\/div><\/div><\/div><\/div>
\n
<\/div>\n\n

\u65e5\u7a0b<\/h2>\n<\/div><\/div>
<\/div><\/div><\/div>
<\/p>\n\n\n\n\n\n\n\n\n\n
\u5fdc\u52df\u671f\u9593<\/th>\n2019\/09\/30\u301c2019\/10\/09<\/td>\n<\/tr>\n
Numpy\u30c6\u30b9\u30c8\u6848\u5185<\/th>\n2019\/10\/11<\/td>\n<\/tr>\n
Numpy\u30c6\u30b9\u30c8<\/th>\n2019\/10\/11\u301c2019\/10\/15<\/td>\n<\/tr>\n
\u53d7\u8b1b\u53ef\u5426\u901a\u77e5<\/th>\n2019\/10\/18 \u4e88\u5b9a<\/td>\n<\/tr>\n
\u7b2c1\u56de\u30b3\u30f3\u30c6\u30f3\u30c4\u914d\u4fe1<\/th>\n2019\/10\/25<\/td>\n<\/tr>\n
\u6700\u7d42\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u53d6\u308a\u7d44\u307f\u671f\u9593<\/th>\n2019\/12\u301c2020\/1<\/td>\n<\/tr>\n
\u4fee\u4e86\u8005\u61c7\u89aa\u4f1a<\/th>\n2020\/3 \u4e88\u5b9a<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div>
<\/div><\/div><\/div>
\n

\u8b1b\u5ea7\u6982\u8981 \/ \u52df\u96c6\u8981\u9805<\/h2>\n