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
- Vue--组件嵌套
1.全局注册: 组件放到components文件夹内,建议组件名是什么行为的name名就是什么 main.js 引入组件:import Users from '组件位置' 注册全局组件:Vue.com ...
- NOI 2002 贪吃的九头龙
树形dp #include<bits/stdc++.h> #define N 305 using namespace std; struct LEB{ int to,nxt,w; }e[N ...
- Let's Encrypt:初次使用免费的ssl证书,并生成java用的 jks(keystore) 文件
现在都流行 https,今天晚上花了二个小时,学习了一下,这里做个学习总结: 因为刚开始接触,就使用免费的:Let's Encrypt Let's Encrypt证书特点: 1. 现在主流的浏览器(c ...
- c++ sort
老是搞混 return bool eg. bool cmp(node a,node b) { if (a.score==b.score) ; else return a.score>b.scor ...
- Altium Designer 18 ------ 常用功能记录
PCB选中某条线路,按一下 Tab 键选中整条线路 PCB中,按 “N” 键选择隐藏或显示某个网络 配置Altium Designer 18 教程所需的捕捉网格的值: G显示Snap Grid菜单,您 ...
- 三层结构、MVC的简介
以前总是听说什么三层结构.什么MVC,但是一直傻傻分不清这是什么意思,下面来简单介绍一下它们吧~ 1.三层结构 在 B/S 架构中,系统标准的三层架构包括:表现层.业务层.持久层 1)表现层 也就是我 ...
- C++回顾day01---<命名空间>
一:namespace是指标识符的各种控件范围(类java中package) C++语言引入命名空间(Namespace)这一概念主要是为了避免命名冲突,其关键字为 namespace 二:iostr ...
- python 深浅拷贝 for循环删除
###########################总结########################### 1. 基础数据类型补充 大多数的基本数据类型的知识.已经学完了 a='aaaa' ls ...
- excel vlookup简易样例【原】
vlookup功能 vlookup主要用来做映射,就像java的map一样. 比如我要找id为2的学生对应的名字,那么在F7单元格录入=VLOOKUP(E7,$A$2:$B$4,2,FALSE) 实际 ...
- linux下使用sftp【转】
. 本文完全引用自: http://www.cnblogs.com/kaituorensheng/p/5797753.html 何为sftp sftp是Secure File Transfer Pro ...