关于人工智能:南瓜书第三章

46次阅读

共计 779 个字符,预计需要花费 2 分钟才能阅读完成。

3.5

$$\cfrac{\partial E_{(w, b)}}{\partial w}=2\left(w \sum\_{i=1}^{m} x_{i}^{2}-\sum\_{i=1}^{m}\left(y_{i}-b\right) x_{i}\right)$$
[推导]:已知 $E_{(w, b)}=\sum\limits\_{i=1}^{m}\left(y_{i}-w x_{i}-b\right)^{2}$,所以
$$\begin{aligned}
\cfrac{\partial E_{(w, b)}}{\partial w}&=\cfrac{\partial}{\partial w} \left[\sum\_{i=1}^{m}\left(y_{i}-w x_{i}-b\right)^{2}\right] \\
&= \sum\_{i=1}^{m}\cfrac{\partial}{\partial w} \left[\left(y_{i}-w x_{i}-b\right)^{2}\right] \\
&= \sum\_{i=1}^{m}\left[2\cdot\left(y_{i}-w x_{i}-b\right)\cdot (-x_i)\right] \\
&= \sum\_{i=1}^{m}\left[2\cdot\left(w x_{i}^2-y_i x_i +bx_i\right)\right] \\
&= 2\cdot\left(w\sum\_{i=1}^{m} x_{i}^2-\sum\_{i=1}^{m}y_i x_i +b\sum\_{i=1}^{m}x_i\right) \\
&=2\left(w \sum\_{i=1}^{m} x_{i}^{2}-\sum\_{i=1}^{m}\left(y_{i}-b\right) x_{i}\right)
\end{aligned}$$

因公式展现问题,请跳转 残缺章节

正文完
 0