{"version":"1.0","blog_title":"\u307f\u30fc\u306e\u307a\u30fc\u3058","image_url":null,"blog_url":"https://pc.atsuhiro-me.net/","author_url":"https://blog.hatena.ne.jp/atsuhiro-me/","type":"rich","categories":["\u6a5f\u68b0\u5b66\u7fd2"],"published":"2023-10-19 23:47:54","description":"\u81ea\u5206\u7528\u30e1\u30e2\u3067\u3059\uff0e autoencoding autoregressive batch normalization broadcasting causal computational graph convolution convolutional criterion derivative dropout embedding finetune gradient gradient descent method large language models (LLM) learning rate loss function natural language processing normalize on\u2026","url":"https://pc.atsuhiro-me.net/entry/2023/10/19/234754","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fpc.atsuhiro-me.net%2Fentry%2F2023%2F10%2F19%2F234754\" title=\"\u6a5f\u68b0\u5b66\u7fd2\u306e\u7528\u8a9e\u3068\u82f1\u5358\u8a9e - \u307f\u30fc\u306e\u307a\u30fc\u3058\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","provider_name":"Hatena Blog","width":"100%","title":"\u6a5f\u68b0\u5b66\u7fd2\u306e\u7528\u8a9e\u3068\u82f1\u5358\u8a9e","height":"190","author_name":"atsuhiro-me","provider_url":"https://hatena.blog"}