摘要：
单层感知机 $$ \begin{aligned} & y = XW + b \ & y = \sum x_i*w_i+b\ \end{aligned} $$ Derivative $$ \begin{aligned} &E=\frac{1}{2}(O^1_0-t)^2\ &\frac{\delta
阅读全文
posted @ 2022-01-18 18:58
Carraway
阅读(61)
推荐(0)
编辑
摘要：
Derivative Rules $$ \begin{aligned} &\frac{\delta E}{\delta w^1_{jk}}=\frac{\delta E}{\delta O_k^1}\frac{\delta O_k^1}{\delta w^1_{jk}}=\frac{\delta E
阅读全文
posted @ 2022-01-18 18:55
Carraway
阅读(35)
推荐(0)
编辑
摘要：
MLP backward $$ \begin{aligned} &For \space an \space output \space layer \space node \space k\in K\ &\frac{\delta E}{\delta W_{jk}}=O_j\delta_k\ &whe
阅读全文
posted @ 2022-01-18 18:54
Carraway
阅读(34)
推荐(0)
编辑
摘要：
Minima $$ f(x,y)=(x^2+y-11)^2+(x+y^2-7)^2 $$ $$ f(3.0, 2.0)=0.0\ f(-2.8505118, 3.131312)=0.0\ f(-3.779310, -3.283186)=0.0\ f(3.584428, -1.84126)=0.0\
阅读全文
posted @ 2022-01-18 18:54
Carraway
阅读(31)
推荐(0)
编辑
