{"provider_name":"Hatena Blog","provider_url":"https://hatena.blog","published":"2020-07-01 00:37:58","categories":["machine_learning"],"image_url":null,"html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Frandommemory.hatenablog.com%2Fentry%2F2020%2F07%2F01%2F003758\" title=\"VAE (Variational Autoencoder) \u8ad6\u6587\u3092\u8aad\u3093\u3067\u307f\u308b - \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>","url":"https://randommemory.hatenablog.com/entry/2020/07/01/003758","author_url":"https://blog.hatena.ne.jp/derwind/","author_name":"derwind","height":"190","blog_title":"\u3089\u3093\u3060\u3080\u306a\u8a18\u61b6","type":"rich","version":"1.0","width":"100%","title":"VAE (Variational Autoencoder) \u8ad6\u6587\u3092\u8aad\u3093\u3067\u307f\u308b","description":"VAE (Variational Autoencoder) - \u3089\u3093\u3060\u3080\u306a\u8a18\u61b6\u3092\u5c11\u3057\u8aad\u3093\u3067\u307f\u3088\u3046\u304b\u306a\u3002\u8aad\u3093\u3067\u898b\u3088\u3046\u304b\u306a\u3068\u66f8\u304d\u3064\u3064\u3082\u5206\u304b\u3089\u306a\u3044\u3068\u3053\u308d\u3092\u7701\u3044\u305f\u305f\u3060\u306e\u7ffb\u8a33\u3068\u3044\u3046\u8aac\u30fb\u30fb\u30fb\u3002\u305f\u3076\u3093\u4ee5\u4e0b\u3067 $p_\\theta (x)$ \u307f\u305f\u3044\u306a\u306e\u306f\u4f8b\u3048\u3070 Bernoulli \u5206\u5e03\u306e\u5bc6\u5ea6\u201c\u51fd\u6570\u201d $p_\\theta (x) = \\theta^x (1-\\theta)^{1-x}$ \u3060\u3068\u304b\u3001\u6b63\u898f\u5206\u5e03\u306e\u5bc6\u5ea6\u51fd\u6570 $p_{\\mu,\\sigma} (x) = \\frac{1}{\\sqrt{2\\pi \\sigma^2}} \\exp \\left\\{ - \\frac{(x - \\mu)^2}{2 \\sigma^2} \\r\u2026","blog_url":"https://randommemory.hatenablog.com/"}