{"categories":["chainer","machine_learning"],"html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fnojima.hatenablog.com%2Fentry%2F2017%2F10%2F17%2F034840\" title=\"EncoderDecoder \u3067\u65e5\u82f1\u7ffb\u8a33\u3092\u3057\u3066\u307f\u305f (\u305d\u306e3) - @nojima&#39;s blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_title":"@nojima's blog","blog_url":"https://nojima.hatenablog.com/","author_url":"https://blog.hatena.ne.jp/nojima718/","version":"1.0","type":"rich","published":"2017-10-17 03:48:40","url":"https://nojima.hatenablog.com/entry/2017/10/17/034840","description":"\u524d\u56de\u304b\u3089\u306e\u7d9a\u304d\u3002 Chainer \u3092\u7528\u3044\u3066\u3001Attention \u3064\u304d\u306e EncoderDecoder \u3092\u5b9f\u88c5\u3059\u308b\u3002 \u30e2\u30c7\u30eb\u306e\u5b9f\u88c5 \u307e\u305a\u306f\u30e2\u30c7\u30eb\u306e\u30b3\u30f3\u30b9\u30c8\u30e9\u30af\u30bf\u3002 \u524d\u56de\u3068\u540c\u3058\u304f\u3001LSTM \u306e\u5b9f\u88c5\u306b\u306f NStepLSTM \u3092\u4f7f\u3063\u305f\u3002 class EncoderDecoder(Chain): def __init__(self, input_dimension: int, output_dimension: int, hidden_dimension: int): super().__init__() with super().init_scope(): self._embed_input = L.\u2026","width":"100%","height":"190","title":"EncoderDecoder \u3067\u65e5\u82f1\u7ffb\u8a33\u3092\u3057\u3066\u307f\u305f (\u305d\u306e3)","provider_url":"https://hatena.blog","provider_name":"Hatena Blog","author_name":"nojima718","image_url":"http://chart.apis.google.com/chart?cht=tx&chl=%20T_y"}