摘要: 一、Activation function Sigmod\[g(z) = \frac{1}{1 + e^{-z}} \] For Binary Classification(Logistic regression)/Output layer is binary. ReLU——most common 阅读全文
posted @ 2025-07-29 19:54 铁鼠 阅读(11) 评论(0) 推荐(0)
摘要: 1.how to build layers Manually(1x3matrix) x = np.arrat([200.0, 17.0]) layer_1 = Dense(units=3, activation='sigmoid') a1 = layer_1(x) layer_2 = Dense(u 阅读全文
posted @ 2025-07-29 15:29 铁鼠 阅读(4) 评论(0) 推荐(0)