4. Deep Learning -- Background & Linear ANN

Linear Regression

  1. 矢量加法按元素相加 要快得多

  2. 噪声 + 极大似然

$$ \begin{gather} \begin{aligned} \pmb y &= \pmb{w^T x} + b + \epsilon \\ \epsilon &\sim \mathcal{N} ( 0, \sigma^2) \end{aligned} \end{gather} $$

$$ \begin{gather} \begin{aligned} P(y| \pmb{ X }) &= \end{aligned} \end{gather} $$

Gradient

Licensed under CC BY-NC-SA 4.0
comments powered by Disqus
Built with Hugo
Theme Stack designed by Jimmy