{"author_url":"https://blog.hatena.ne.jp/HTN20190109/","published":"2026-05-08 23:35:57","type":"rich","provider_url":"https://hatena.blog","blog_title":"HTN20190109\u306e\u65e5\u8a18","height":"190","categories":["DL"],"url":"https://htn20190109.hatenablog.com/entry/2026/05/08/233557","title":"SimpleRnnlm","blog_url":"https://htn20190109.hatenablog.com/","author_name":"HTN20190109","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fhtn20190109.hatenablog.com%2Fentry%2F2026%2F05%2F08%2F233557\" title=\"SimpleRnnlm - HTN20190109\u306e\u65e5\u8a18\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","width":"100%","description":"import numpy as np # =========================# utility# ========================= def softmax(x): x = x - np.max(x, axis=-1, keepdims=True) return np.exp(x) / np.sum(np.exp(x), axis=-1, keepdims=True) # =========================# TimeEmbedding# ========================= class TimeEmbedding: def __i\u2026","version":"1.0","image_url":null,"provider_name":"Hatena Blog"}