{"provider_url":"https://hatena.blog","version":"1.0","blog_url":"https://randommemory.hatenablog.com/","author_name":"derwind","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Frandommemory.hatenablog.com%2Fentry%2F2021%2F11%2F02%2F010951\" title=\"\u30bc\u30ed\u3064\u304f 2 (8) - \u3089\u3093\u3060\u3080\u306a\u8a18\u61b6\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","type":"rich","provider_name":"Hatena Blog","blog_title":"\u3089\u3093\u3060\u3080\u306a\u8a18\u61b6","width":"100%","categories":["machine_learning"],"url":"https://randommemory.hatenablog.com/entry/2021/11/02/010951","title":"\u30bc\u30ed\u3064\u304f 2 (8)","published":"2021-11-02 01:09:51","height":"190","description":"https://github.com/oreilly-japan/deep-learning-from-scratch-2/blob/84cb914a6469bffcc0ea5302f86df98c453a5767/common/time_layers.py#L316 ls = np.log(ys[np.arange(N * T), ts]) \u304c\u30d4\u30f3\u3068\u6765\u306a\u3044\u306e\u3067\u5b9f\u9a13\u3002 >>> ys = np.array([[1,2],[3,4],[5,6],[7,8],[9,10]]) >>> ts = np.array([0,0,1,1,0]) >>> ys[np.arange(5), ts] array(\u2026","image_url":null,"author_url":"https://blog.hatena.ne.jp/derwind/"}