Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week2, Optimization algorithms
Gradient descent
Batch Gradient Decent, Mini-batch gradient descent, Stochastic gradient descent



还有很多比gradient decent 更优化的算法,在了解这些算法前,需要先理解 Exponentially weighted averages 这个概念



Exponentially weighted average 是一种计算平均值的方法,非常省storage 和 memory, 但是不是很精确。 然后引出一个bias correction 的概念,就是为了能使得 Exponentially weighted average 更加精确.

momentum (or called Gradient descent with momentum)
传统的Gradient descent 算法有如下图所示的问题 - 每次迭代都会来回跳动,不直接指向optimum, 在没有做feature scaling 的时候尤其明显。所以引出一个修正的算法 - Gradient descent with momentum.


RMSprop
目的和上面讲到的Momentum是一样的,就是使得每次迭代都尽量指向optimum而不是来回跳动. 算法实现如下. RMSprop带来的好处是迭代更快,和可以选用更大的learning rate.

Adam optimation algorithm:
结合了Momentum 和 RMSprop 两种算法. Adam stands for Adaptive mement estimation.


Learning rate decay
why? to reduce the oscillation near the central point.

有哪些实现方式呢?


Local optima and saddle point
在大型神经网络里,saddle point 可能比local optima更常见.


Ref:
Coursera, Deep leaning, Andrew Ng
Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week2, Optimization algorithms的更多相关文章
- 《Improving Deep Neural Networks:Hyperparameter tuning, Regularization and Optimization》课堂笔记
Lesson 2 Improving Deep Neural Networks:Hyperparameter tuning, Regularization and Optimization 这篇文章其 ...
- [C4] Andrew Ng - Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
About this Course This course will teach you the "magic" of getting deep learning to work ...
- Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week1, Assignment(Initialization)
声明:所有内容来自coursera,作为个人学习笔记记录在这里. Initialization Welcome to the first assignment of "Improving D ...
- Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week1, Assignment(Gradient Checking)
声明:所有内容来自coursera,作为个人学习笔记记录在这里. Gradient Checking Welcome to the final assignment for this week! In ...
- Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week1, Assignment(Regularization)
声明:所有内容来自coursera,作为个人学习笔记记录在这里. Regularization Welcome to the second assignment of this week. Deep ...
- Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week2, Assignment(Optimization Methods)
声明:所有内容来自coursera,作为个人学习笔记记录在这里. 请不要ctrl+c/ctrl+v作业. Optimization Methods Until now, you've always u ...
- 课程二(Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization),第一周(Practical aspects of Deep Learning) —— 4.Programming assignments:Gradient Checking
Gradient Checking Welcome to this week's third programming assignment! You will be implementing grad ...
- 吴恩达《深度学习》-课后测验-第二门课 (Improving Deep Neural Networks:Hyperparameter tuning, Regularization and Optimization)-Week 1 - Practical aspects of deep learning(第一周测验 - 深度学习的实践)
Week 1 Quiz - Practical aspects of deep learning(第一周测验 - 深度学习的实践) \1. If you have 10,000,000 example ...
- 吴恩达《深度学习》-第二门课 (Improving Deep Neural Networks:Hyperparameter tuning, Regularization and Optimization)-第一周:深度学习的实践层面 (Practical aspects of Deep Learning) -课程笔记
第一周:深度学习的实践层面 (Practical aspects of Deep Learning) 1.1 训练,验证,测试集(Train / Dev / Test sets) 创建新应用的过程中, ...
- 课程二(Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization),第三周(Hyperparameter tuning, Batch Normalization and Programming Frameworks) —— 2.Programming assignments
Tensorflow Welcome to the Tensorflow Tutorial! In this notebook you will learn all the basics of Ten ...
随机推荐
- Windows下VMware14黑屏
解决方法 以管理员身份运行命令提示符,执行netsh winsock reset
- HEOI2019 游记——240秒处的起死回生
我还没死 Day-1 最后一场模拟赛! T1:自然数幂次和再前缀和,还是O(k)次多项式,拉格朗日插值,,,,,不能总想斯特林数啊!!! T2:神仙DP预处理... T3:AC自动机+LCA处差分+暴 ...
- 洛谷P5111 zhtobu3232的线段树
题意:给定线段树,上面若干个节点坏了,求能表示出多少区间. 区间能被表示出当且仅当拆出来的log个节点都是好的. 解:每个区间在最浅的节点处计算答案. 对于每个节点维护从左边过来能有多少区间,从右边过 ...
- [luogu4309][最长上升子序列]
题目链接 思路 因为这些数字是从小到大加进去的,所以以当前数字结尾的最长上升子序列可以从前面位置的任何一个数字转移过来.所以只要能知道每个数字最终位于哪个位置就行了. 没想到出了treap还有什么办法 ...
- 封装一个基于NLog+NLog.Mongo的日志记录工具类LogUtil,nloglogutil
封装一个基于NLog+NLog.Mongo的日志记录工具类LogUtil,代码比较简单,主要是把MongoTarget的配置.FileTarget的配置集成到类中,同时利用缓存依赖来判断是否需要重新创 ...
- gei 操作
git --version 查看版本号 进入项目文件 上传账号的用户名git config --global user.name "牛星宇" 上传账号的邮箱git config - ...
- java面试——问题回溯
背景:用来记录面试过程中遇到的问题,在这里进行记录,下次不要犯同样的错误. 迪普科技 Linux服务器下的top命令 #动态更新的虚拟文件实际上是许多其他内存相关工具(如:free / ps / to ...
- 洛谷 P1061 Jam的计数法
传送门 题解: 相关变量解释: int s,t,w; ;//最多输出五组 int maxNum[maxn];//maxNum[i] : i 位置可以达到的最大值 char letter[maxn]; ...
- Linux 上 nginx配置
1:安装工具包 wget.vim和gcc yum install -y wget yum install -y vim-enhanced yum install -y make cmake gcc g ...
- asp.net 获得伪静态网址解决微信sdk签名问题
手机网站是asp.net c#编写的,前几天因为要使用微信SDK在手机网站页面使用分享功能,但是程序使用了伪静态功能.如果原地址是:http://ww.xx.com/news/show.aspx?id ...