RNN(Recurrent Neural Network)的几个难点
1. vanish of gradient
RNN的error相对于某个时间点t的梯度为:
\(\frac{\partial E_t}{\partial W}=\sum_{k=1}^{t}\frac{\partial E_t}{\partial y_t}\frac{\partial y_t}{\partial h_i}\frac{\partial h_t}{\partial h_k}\frac{\partial h_k}{\partial W}\) (公式1),
其中\(h\)是hidden node的输出,\(y_t\)是网络在t时刻的output,\(W\)是hidden nodes 到hidden nodes的weight,而\(\frac{\partial h_t}{\partial h_k}\)是导数在时间段[k,t]上的链式展开,这段时间可能很长,会造成vanish或者explosion gradiant。将\(\frac{\partial h_t}{\partial h_k}\)沿时间展开:\(\frac{\partial h_t}{\partial h_k}=\prod_{j=k+1}^{t}\frac{\partial h_j}{\partial h_{j-1}}=\prod_{j=k+1}^{t}W^T \times diag [\frac{\partial\sigma(h_{j-1})}{\partial h_{j-1}}]\)。上式中的diag矩阵是个什么鬼?我来举个例子,你就明白了。假设现在要求解\(\frac{\partial h_5}{\partial h_4}\),回忆向前传播时\(h_5\)是怎么得到的:\(h_5=W\sigma(h_4)+W^{hx}x_4\),则\(\frac{\partial h_5}{\partial h_4}=W\frac{\partial \sigma(h_4)}{\partial h_4}\),注意到\(\sigma(h_4)\)和\(h_4\)都是向量(维度为D),所以\(\frac{\partial \sigma(h_4)}{\partial h_4}\)是Jacobian矩阵也即:\(\frac{\partial \sigma(h_4)}{\partial h_4}=\) \(\begin{bmatrix} \frac{\partial\sigma_1(h_{41})}{\partial h_{41}}&\cdots&\frac{\partial\sigma_1(h_{41})}{\partial h_{4D}} \\ \vdots&\cdots&\vdots \\ \frac{\partial\sigma_D(h_{4D})}{\partial h_{41}}&\cdots&\frac{\partial\sigma_D(h_{4D})}{\partial h_{4D}}\end{bmatrix}\),明显的,非对角线上的值都是0。这是因为sigmoid logistic function \(\sigma\)是element-wise的操作。
后面推导vanish或者explosion gradiant的过程就很简单了,我就不写了,请参考http://cs224d.stanford.edu/lecture_notes/LectureNotes4.pdf 中的公式(14)往后部分。
2. weight shared (tied) 时, the gradient of tied weight = sum of gradient of individual weights
举个例子你就明白了:假设有向前传播\(y=F[W_1f(W_2x)]\), 且weights \(W_1\) \(W_2\) tied, 现在要求gradient \(\frac{\partial y}{\partial W}\)
办法一:
先求gradient \(\frac{\partial F[]}{\partial W_2} = F'[]f() \)
再求gradient \(\frac{\partial F[]}{\partial W_1} = F'[] (W_2f'()x) \)
将上两式相加后得,\(F'[]f()+F'[] (W_2f'()x)=F'[](f()+W_2f'()x)\)
假设weights \(W_1\) \(W_2\) tied,则上式=\(F'[](f()+Wf'()x) = \frac{\partial y}{\partial W} \)
办法二:
现在我们换个办法,在假设weights \(W_1\) \(W_2\) tied的基础上,直接求gradient
\(\frac{\partial y}{\partial W} = F'[]( \frac{\partial Wf()}{\partial W} + W \frac{\partial f()}{\partial W} ) = F'[](f()+Wf'()x) \)
可见,两种方法的结果是一样的。所以,当权重共享时,关于权重的梯度=两个不同权重梯度的和。
3. LSTM & Gated Recurrent units 是如何避免vanish的?
To understand this, you will have to go through some math. The most accessible article wrt recurrent gradient problems IMHO is Pascanu's ICML2013 paper [1].
A summary: vanishing/exploding gradient comes from the repeated application of the recurrent weight matrix [2]. That the spectral radius of the recurrent weight matrix is bigger than 1 makes exploding gradients possible (it is a necessary condition), while a spectral radius smaller than 1 makes it vanish, which is a sufficient condition.
Now, if gradients vanish, that does not mean that all gradients vanish. Only some of them, gradient information local in time will still be present. That means, you might still have a non-zero gradient--but it will not contain long term information. That's because some gradient g + 0 is still g. (上文中公式1,因为是相加,所以有些为0,也不会引起全部为0)
If gradients explode, all of them do. That is because some gradient g + infinity is infinity.(上文中公式1,因为是相加,所以有些为无限大,会引起全部为无限大)
That is the reason why LSTM does not protect you from exploding gradients, since LSTM also uses a recurrent weight matrix(h(t) = o(t) ◦ tanh(c(t))?), not only internal state-to-state connections( c(t) = f (t) ◦ ˜c(t−1) +i(t) ◦ ˜c(t) h(t)). Successful LSTM applications typically use gradient clipping.
LSTM overcomes the vanishing gradient problem, though. That is because if you look at the derivative of the internal state at T to the internal state at T-1, there is no repeated weight application. The derivative actually is the value of the forget gate. And to avoid that this becomes zero, we need to initialise it properly in the beginning.
That makes it clear why the states can act as "a wormhole through time", because they can bridge long time lags and then (if the time is right) "re inject" it into the other parts of the net by opening the output gate.
[1] Pascanu, Razvan, Tomas Mikolov, and Yoshua Bengio. "On the difficulty of training recurrent neural networks." arXiv preprint arXiv:1211.5063 (2012).
[2] It might "vanish" also due to saturating nonlinearities, but that is sth that can also happen in shallow nets and can be overcome with more careful weight initialisations.
ref: Recursive Deep Learning for Natural Language Processing and Computer Vision.pdf
CS224D-3-note bp.pdf
未完待续。。。
RNN(Recurrent Neural Network)的几个难点的更多相关文章
- Recurrent Neural Network系列2--利用Python,Theano实现RNN
作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 本文翻译自 RECURRENT NEURAL NETWORKS T ...
- Recurrent Neural Network系列3--理解RNN的BPTT算法和梯度消失
作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 这是RNN教程的第三部分. 在前面的教程中,我们从头实现了一个循环 ...
- 循环神经网络(Recurrent Neural Network,RNN)
为什么使用序列模型(sequence model)?标准的全连接神经网络(fully connected neural network)处理序列会有两个问题:1)全连接神经网络输入层和输出层长度固定, ...
- Recurrent neural network (RNN) - Pytorch版
import torch import torch.nn as nn import torchvision import torchvision.transforms as transforms # ...
- 4.5 RNN循环神经网络(recurrent neural network)
自己开发了一个股票智能分析软件,功能很强大,需要的点击下面的链接获取: https://www.cnblogs.com/bclshuai/p/11380657.html 1.1 RNN循环神经网络 ...
- Recurrent Neural Network系列1--RNN(循环神经网络)概述
作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 本文翻译自 RECURRENT NEURAL NETWORKS T ...
- Recurrent Neural Network(循环神经网络)
Reference: Alex Graves的[Supervised Sequence Labelling with RecurrentNeural Networks] Alex是RNN最著名变种 ...
- 循环神经网络(RNN, Recurrent Neural Networks)介绍(转载)
循环神经网络(RNN, Recurrent Neural Networks)介绍 这篇文章很多内容是参考:http://www.wildml.com/2015/09/recurrent-neur ...
- Recurrent Neural Network系列4--利用Python,Theano实现GRU或LSTM
yi作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 本文翻译自 RECURRENT NEURAL NETWORK ...
- Recurrent Neural Network[Content]
下面的RNN,LSTM,GRU模型图来自这里 简单的综述 1. RNN 图1.1 标准RNN模型的结构 2. BiRNN 3. LSTM 图3.1 LSTM模型的结构 4. Clockwork RNN ...
随机推荐
- 小强的HTML5移动开发之路(2)——HTML5的新特性
来自:http://blog.csdn.net/dawanganban/article/details/17592787 一.画布(Canvas) 画布是网页中的一块区域,可所以用JavaScript ...
- 修改DrawerLayout 和toolbar 配合navigation的颜色
大家都知道DrawerLayout 和toolbar 结合能出来高大上的效果. 使用到一个ActionBarDrawerToggle类. 那么怎么修改DrawerToggle的颜色呢,搜索了很多中文网 ...
- hibernate关联对象的增删改查------增
本文可作为,北京尚学堂马士兵hibernate课程的学习笔记. 这一节,我们看看hibernate关联关系的增删改查 就关联关系而已,咱们在上一节已经提了很多了,一对多,多对一,单向,双向... 其实 ...
- VS2005宏无法运行的问题(打了补丁MS14-009之后)
VS2005宏无法运行的问题(打了补丁MS14-009之后) 部门很多同事都是使用VS的宏来给源文件添加文件头,给函数.类添加注释等等,大概是14年2月份之后(根据lucifer提供的时间),这些宏突 ...
- STL常用查找算法介绍
adjacent_find() 在iterator对标识元素范围内,查找一对相邻重复元素,找到则返回指向这对元素的第一个元素的迭代器.否则返回past-the-end. #include <io ...
- com.android.ddmlib.SyncException: Read-only file system
通过eclipse运行Android 程序到测试机时候 控制台出现如下错误: [2014-02-13 15:06:03 - MPlay] Failed to install MPlay.apk on ...
- 套接字编程相关函数(1:套接字地址结构、字节序转换、IP地址转换)
1. 套接字地址结构 1.1 IPv4套接字地址结构 IPv4套接字地址结构通常也称为“网际套接字地址结构”,它以sockaddr_in命名,定义在<netinet/in.h>头文件中.下 ...
- Gradle 1.12用户指南翻译——第二十二章. 标准的 Gradle 插件
其他章节的翻译请参见: http://blog.csdn.net/column/details/gradle-translation.html 翻译项目请关注Github上的地址: https://g ...
- 在Windows使用git工具将代码同步至github(作者:ying1989920)
[ps]git是一个分布式代码管理工具,类似于svn,方便协同开发,git里面有所谓的仓库(用来存放代码的),分为本地和线上,线上的你可以自己搭建,不想搭建的话github就给你提供了. [关于 ...
- LeetCode之“动态规划”:Maximum Subarray
题目链接 题目要求: Find the contiguous subarray within an array (containing at least one number) which has t ...