摘要：
Activation Functions Sigmoid/Logstic 可能有梯度离散现象（导数接近0时） MSE $$ \begin{aligned} &loss = \sum[y-(xw+b)]^2\ &L2 -norm = ||y-(xw+b)||2\ &loss = norm(y-(xw+
阅读全文
摘要：
Gradient Clarificaton 导数,derivate 偏微分,partial derivate 梯度,gradient $$ \begin{aligned} &\bigtriangledown{f} = (\frac{\delta{f}}{\delta{x_1}};\frac{\del
阅读全文
