Skip to content

Commit

Permalink
更新资源
Browse files Browse the repository at this point in the history
  • Loading branch information
km1994 committed Mar 1, 2021
1 parent 20e2085 commit 6c533af
Show file tree
Hide file tree
Showing 3 changed files with 3 additions and 1 deletion.
2 changes: 1 addition & 1 deletion BasicAlgorithm/激活函数.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ sigmoid 函数 能够把输入的连续实值变换为0和1之间的输出,特

#### 2.1.3 sigmoid 函数 有什么缺点?

1. 在深度神经网络中梯度反向传递时导致梯度爆炸和梯度消失,其中梯度爆炸发生的概率非常小,而梯度消失发生的概率比较大
1. 如果我们初始化神经网络的权值为[0,1]之间的随机数,由反向传播算法的数学推导可以知道,梯度从后向前传播时,每传递一层梯度值都会下降为原来原来的0.25倍,如果神经网络层比较多是时,那么梯度会穿过多层之后变得接近于0,也就出现梯度消失问题,当权值初始化为 [1,+]期间内的值时,则会出现梯度爆炸问题

![](img/微信截图_20201228220429.png)

Expand Down
2 changes: 2 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@

> 作者:杨夕、芙蕖、李玲、陈海顺、twilight、LeoLRH、杜晓东、艾春辉、张永泰、金金金
![](other_study/resource/pic/微信截图_20210301212242.png)

![](img/微信截图_20210212153059.png)

## 介绍
Expand Down
Binary file added img/微信截图_20210301212242.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 6c533af

Please sign in to comment.