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

  1. [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, ...

  2. 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 ...

  3. 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 ...

  4. 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 ...

  5. 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 ...

  6. 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 ...

  7. 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 ...

  8. [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 ________ ...

  9. 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

  1. 粉红猪小妹peppa pig中英文版209集+218本绘本+音频

    1.avi格式英文版包括,第一季52集有外挂英文字幕,第二季53集外挂英文字幕,第三季52集有外挂同步英文字幕,第四季1到39集有英文字幕,40-52无字幕.另有4季音频(每集都是单独的音频文件,方便 ...

  2. [WC2019] 数树

    [WC2019] 数树 Zhang_RQ题解(本篇仅概述) 前言 有进步,只做了半天.... 一道具有极强综合性的数数好题! 强大的多合一题目 精确地数学推导和耐心. 有套路又不失心意. 融合了: 算 ...

  3. 分布式监控系统Zabbix--使用Grafana进行图形展示

      今天介绍一款高颜值监控绘图工具Grafana,在使用Zabbix监控环境中,通常我们会结合Grafana进行图形展示.Grafana默认没有zabbix作为数据源,需要手动给zabbix安装一个插 ...

  4. WebAPI接口安全校验

    通过网上查看相关WebAPI接口验证的方法,整理了一下,直接上代码,功能不复杂,有问题留言, //--------------------------------------------------- ...

  5. (转)CDN的作用与基本过程

    背景:积累大型网站开发中需要掌握的技术. CDN的作用与基本过程 https://blog.csdn.net/lihao21/article/details/52808747#comments CDN ...

  6. django2+uwsgi+nginx上线部署到服务器Ubuntu16.04(最新最详细版)

    1.前期准备 1.打开Terminal终端,执行以下命令,将项目所需要的依赖包,都记录到一个文件内备用. pip freeze >requirements.txt 2.将项目文件夹→右键→添加压 ...

  7. sed 的|

    #!/bin/bash/etc/init.d/nginx start && \sed -i "s|/project/env/|/${PROJ}/${ENVT}/|g" ...

  8. qml: C++调用qml函数

    C++调用qml函数,是通过下面的函数实现的: bool QMetaObject::invokeMethod(QObject *obj, const char *member, Qt::Connect ...

  9. 2017-12-15python全栈9期第二天第七节之运算符

    #!/user/bin/python# -*- coding:utf-8 -*-print(3>4 or 4<3 and 1==1)print(1<2 and 3 <4 or ...

  10. Python package下载中遇到ReadTimeoutError: HTTPSConnectionPool?

    问题描述: Python package下载中遇到ReadTimeoutError: HTTPSConnectionPool? 问题解决: 方法1:继续重复下载 pip install virtual ...