{"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%2F2019%2F11%2F06%2F022726\" title=\"\u81ea\u52d5\u5fae\u5206 - \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>","title":"\u81ea\u52d5\u5fae\u5206","author_url":"https://blog.hatena.ne.jp/derwind/","height":"190","published":"2019-11-06 02:27:26","url":"https://randommemory.hatenablog.com/entry/2019/11/06/022726","provider_name":"Hatena Blog","type":"rich","image_url":null,"provider_url":"https://hatena.blog","description":"\\begin{align} \\frac{d}{d x} (x^2)^2\\Big|_{x=3} = 108 \\end{align}\u3092\u81ea\u52d5\u5fae\u5206\u3067\u6c42\u3081\u3066\u307f\u307e\u3057\u3087\u30fb\u30fb\u30fb\u3068\u3044\u3046\u3060\u3051\u3002[TensorFlow] x = tf.constant(3.0) with tf.GradientTape() as t: t.watch(x) y = x * x z = y * y dz_dx = t.gradient(z, x) print(dz_dx) tf.Tensor(108.0, shape=(), dtype=float32) [PyTorch] x = torch.tensor(3.0, requires\u2026","width":"100%","blog_title":"\u3089\u3093\u3060\u3080\u306a\u8a18\u61b6","categories":["machine_learning"],"version":"1.0"}