Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week3, Hyperparameter tuning, Batch Normalization and Programming Frameworks
Tuning process
下图中的需要tune的parameter的先后顺序, 红色>黄色>紫色,其他基本不会tune.
先讲到怎么选hyperparameter, 需要随机选取(sampling at random)
随机选取的过程中,可以采用从粗到细的方法逐步确定参数

有些参数可以按照线性随机选取, 比如 n[l]

但是有些参数就不适合线性的sampling at radom, 比如 learning rate α,这时可以用 log


Andrew 很幽默的讲到了两种选参数的实际场景 pandas vs caviar. pandas approach 一般用在你的算力不够时候,要持续几天的training.

Batch norm
我们知道对input layer 做 normalizing, 其实对每一层的输入都可以做normalizing, 这就是 batch norm. 做batch norm 时,有对 activation后的结果做norm 的,也有对activation 前的结果 z 做batch norm 的,这里讲的是后一种,对z 做norm.




为什么Batch Norm 起作用呢?
先看下下面图讲到的convariate shift,如果traing set 的distribution 变了,就应该重新train model. 同样,对NN的每一层也有类似的问题.

Andrew讲到batch norm 是为了尽量使得不同layer decouple,这样相互影响就要小一点,整个NN比较稳定.

Batch norm 还有regularization 的作用,但是这个算法主要不是做这个的. 不建议专门用它来做regularization.

对 test set 求 μ, σ2, 采用了不一样的方法,就是基于签名mini-batch set 求出来的μ, σ2 应用exponetially weighted average 求平均值. 它和logistic regression 一样,decision boudary 是线性的.

Softmax Regression
Softmax regression 就是 logistic regression 的generaliazation 版本, 它可以用在multi-class clarification 问题上。和logistic regression 一样,decision boudary 都是线性的. 如果要使得decison boudary 是非线性的就需要deep network.



Programing framework
TensorFlow by google, an example

Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week3, Hyperparameter tuning, Batch Normalization and Programming Frameworks的更多相关文章
- [C2W3] Improving Deep Neural Networks : Hyperparameter tuning, Batch Normalization and Programming Frameworks
第三周:Hyperparameter tuning, Batch Normalization and Programming Frameworks 调试处理(Tuning process) 目前为止, ...
- 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 ...
- 吴恩达《深度学习》-课后测验-第一门课 (Neural Networks and Deep Learning)-Week 3 - Shallow Neural Networks(第三周测验 - 浅层神 经网络)
Week 3 Quiz - Shallow Neural Networks(第三周测验 - 浅层神经网络) \1. Which of the following are true? (Check al ...
- [CS231n-CNN] Training Neural Networks Part 1 : activation functions, weight initialization, gradient flow, batch normalization | babysitting the learning process, hyperparameter optimization
课程主页:http://cs231n.stanford.edu/ Introduction to neural networks -Training Neural Network ________ ...
- Coursera, Deep Learning 2, Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week1, Course
Train/Dev/Test set Bias/Variance Regularization 有下面一些regularization的方法. L2 regularation drop out da ...
随机推荐
- 洛谷P3980 志愿者招募
题意:懒得写了...... 解: 一开始想的是每天建点,每种人建点,然后连边费用流,发现一个人可以管辖多天,不好处理. 回想起了网络流24题中的"最长k可重线段集","最 ...
- 【P2303】Longge的问题
题目大意:求\[\sum\limits_{i=1}^ngcd(n,i)\] 题解:发现 gcd 中有很多是重复的,因此考虑枚举 gcd. \[\sum\limits_{i=1}^ngcd(n,i)=\ ...
- (转)ZooKeeper的Znode剖析
ZooKeeper的Znode剖析 https://blog.csdn.net/lihao21/article/details/51810395 根据节点的存活时间,可以对节点划分为持久节点和临时节点 ...
- (五)Oracle 的 oracle 表查询
http://www.hechaku.com/Oracle/oracle_tables_chack.html 通过scott用户下的表来演示如何使用select语句,接下来对emp.dept.salg ...
- django跨域请求问题
一 同源策略 同源策略(Same origin policy)是一种约定,它是浏览器最核心也最基本的安全功能,如果缺少了同源策略,则浏览器的正常功能可能都会受到影响.可以说Web是构建在同源策略基础之 ...
- Codeforces Round #523 (Div. 2) D. TV Shows
传送门 https://www.cnblogs.com/violet-acmer/p/10005351.html 题意: 有n个节目,每个节目都有个开始时间和结束时间. 定义x,y分别为租电视需要的花 ...
- Collection中的迭代器
迭代器:boolean hasNext() 判断集合中是否还有没有被取出数据nexe() 取出集合中下一个元素package cn.lijun.demo4; import java.util.Arra ...
- SQLServer 游标详解
一.用到的数据 CREATE TABLE [dbo].[XSB]( ) NOT NULL, ) NOT NULL, [性别] [bit] NULL, [出生时间] [date] NULL, ) NUL ...
- python改文件名
import os file_names = os.listdir('D:\\mobilefile\\_hd') for file_name in file_names : print(file_na ...
- 解决openoffice进程异常退出的办法
步骤1 编写脚本 openoffice.sh #!/usr/bin/bash OPENOFFICEPID=`ps -ef|grep "/opt/openoffice4/program/sof ...