RNN, LSTM introduce and explain the problem to disappear gradient

Written on the front, thanks to these two articles, the framework is basically obtained from these two articles:

https://zhuanlan.zhihu.com/p/28687529

https://zhuanlan.zhihu.com/p/28749444

This is part of the group of students I do share a PPT, here to record it.

Guess you like

Origin www.cnblogs.com/zhouxiaosong/p/11604532.html