{"width":"100%","height":"190","description":"\u904e\u5b66\u7fd2\u306e\u9632\u6b62\u30fb\u5b66\u7fd2\u306e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0 Dropout Batch normalization Resnet Layer Normalization Normalization Layers \u7406\u8ad6 Distilling the knowledge in a neural network Deep neural networks are easily fooled: High confidence predictions for unrecognizable images \u753b\u50cf\u30fb\u52d5\u753b\u304b\u3089\u306e\u30ad\u30e3\u30d7\u30b7\u30e7\u30f3\u751f\u6210 Show, attend and tell: Neural image caption gene\u2026","type":"rich","blog_url":"https://paper.hatenadiary.jp/","author_name":"misos","provider_name":"Hatena Blog","categories":["\u30ea\u30f3\u30af\u96c6","\u6a5f\u68b0\u5b66\u7fd2","\u6df1\u5c64\u5b66\u7fd2","\u8ad6\u6587\u30fb\u8cc7\u6599\u30fb\u30b9\u30e9\u30a4\u30c9\u96c6"],"provider_url":"https://hatena.blog","title":"Deep\u7cfb\u306e\u8ad6\u6587\u3081\u3082\u524d\u534a (2016\u5e74\u590f\u9803\u307e\u3067\u306e\u3082\u306e\u5bfe\u8c61)","version":"1.0","published":"2016-11-03 21:27:11","image_url":null,"url":"https://paper.hatenadiary.jp/entry/2016/11/03/212711","blog_title":"\u3081\u3082","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fpaper.hatenadiary.jp%2Fentry%2F2016%2F11%2F03%2F212711\" title=\"Deep\u7cfb\u306e\u8ad6\u6587\u3081\u3082\u524d\u534a (2016\u5e74\u590f\u9803\u307e\u3067\u306e\u3082\u306e\u5bfe\u8c61) - \u3081\u3082\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","author_url":"https://blog.hatena.ne.jp/misos/"}