lqchenCode
diff --git a/‎formula/Weights_initialization_01.wmf‎
47.1 KB b/‎formula/Weights_initialization_01.wmf‎
47.1 KB
diff --git a/‎formula/Weights_initialization_02.wmf‎
61.9 KB b/‎formula/Weights_initialization_02.wmf‎
61.9 KB
diff --git a/‎readme.md‎
Lines changed: 1 addition & 1 deletion b/‎readme.md‎
Lines changed: 1 addition & 1 deletion
@@ -146,7 +146,7 @@
  - 对于乘法偏置（文中叫 multiplicative bias）`β`的梯度为：![$${{\partial E} \over {\partial {\beta _j}}} = \sum\limits_{u,v} {{{(\delta _{\rm{j}}^l \circ d_j^l)}_{uv}}} $$](http://latex.codecogs.com/gif.latex?%5Clarge%20%24%24%7B%7B%5Cpartial%20E%7D%20%5Cover%20%7B%5Cpartial%20%7B%5Cbeta%20_j%7D%7D%7D%20%3D%20%5Csum%5Climits_%7Bu%2Cv%7D%20%7B%7B%7B%28%5Cdelta%20_%7B%5Crm%7Bj%7D%7D%5El%20%5Ccirc%20d_j%5El%29%7D_%7Buv%7D%7D%7D%20%24%24)，其中![$$d_j^l = down({\rm{x}}_j^{l - 1})$$](http://latex.codecogs.com/gif.latex?%5Clarge%20%24%24d_j%5El%20%3D%20down%28%7B%5Crm%7Bx%7D%7D_j%5E%7Bl%20-%201%7D%29%24%24)
 
 
-## 二、权重初始化问题
+## 二、权重初始化问题1_Sigmoid\tanh\Softsign激励函数
Original file line number	Diff line number	Diff line change
`@@ -146,7 +146,7 @@`
`146`	`146`	- 对于乘法偏置（文中叫 multiplicative bias）`β`的梯度为：![$${{\partial E} \over {\partial {\beta _j}}} = \sum\limits_{u,v} {{{(\delta _{\rm{j}}^l \circ d_j^l)}_{uv}}} $$](http://latex.codecogs.com/gif.latex?%5Clarge%20%24%24%7B%7B%5Cpartial%20E%7D%20%5Cover%20%7B%5Cpartial%20%7B%5Cbeta%20_j%7D%7D%7D%20%3D%20%5Csum%5Climits_%7Bu%2Cv%7D%20%7B%7B%7B%28%5Cdelta%20_%7B%5Crm%7Bj%7D%7D%5El%20%5Ccirc%20d_j%5El%29%7D_%7Buv%7D%7D%7D%20%24%24)，其中![$$d_j^l = down({\rm{x}}_j^{l - 1})$$](http://latex.codecogs.com/gif.latex?%5Clarge%20%24%24d_j%5El%20%3D%20down%28%7B%5Crm%7Bx%7D%7D_j%5E%7Bl%20-%201%7D%29%24%24)
`147`	`147`
`148`	`148`
`149`		`-## 二、权重初始化问题`
	`149`	`+## 二、权重初始化问题1_Sigmoid\tanh\Softsign激励函数`
`150`	`150`
`151`	`151`
`152`	`152`