1. Underfit = High bias

　 Overfit = High varience

2. Addressing overfitting:

　　(1) reduce number of features.

　　　　Manually select which features to keep.

　　　　Model selection algorithm

disadvantage: throw out some useful information

(2) Regularization

　　　　Keep all the features, but reduce magnitude/values of parameters θj

　　　　works well when we have a lot of features, each of which contributλes a bit to predicting y.

3. Regularization

if λ is extremely large, , then J(θ) will be underfitting

4. Gradient desent

Repeat {

　　

　　       (j = 1, 2 ... n)

}

5. Normal equation

if λ > 0

if m <= n

is non-invertible/singular

but using regularization will avoid this problem

Machine Learning No.4: Regularization的更多相关文章

  1. [笔记]机器学习(Machine Learning) - 03.正则化(Regularization)

    欠拟合(Underfitting)与过拟合(Overfitting) 上面两张图分别是回归问题和分类问题的欠拟合和过度拟合的例子.可以看到,如果使用直线(两组图的第一张)来拟合训,并不能很好地适应我们 ...

  2. Machine Learning - 第3周（Logistic Regression、Regularization）

    Logistic regression is a method for classifying data into discrete outcomes. For example, we might u ...

  3. （原创）Stanford Machine Learning (by Andrew NG) --- (week 3) Logistic Regression & Regularization

    coursera上面Andrew NG的Machine learning课程地址为:https://www.coursera.org/course/ml 我曾经使用Logistic Regressio ...

  4. Regularization method for machine learning

    Regularization method(正则化方法) Outline Overview of Regularization L0 regularization L1 regularization ...

  5. Andrew Ng Machine Learning 专题【Logistic Regression &amp; Regularization】

    此文是斯坦福大学,机器学习界 superstar - Andrew Ng 所开设的 Coursera 课程:Machine Learning 的课程笔记. 力求简洁,仅代表本人观点,不足之处希望大家探 ...

  6. machine learning(14) --Regularization:Regularized linear regression

    machine learning(13) --Regularization:Regularized linear regression Gradient descent without regular ...

  7. Kernel Functions for Machine Learning Applications

    In recent years, Kernel methods have received major attention, particularly due to the increased pop ...

  8. Machine Learning Algorithms Study Notes(3)--Learning Theory

    Machine Learning Algorithms Study Notes 高雪松 @雪松Cedro Microsoft MVP 本系列文章是Andrew Ng 在斯坦福的机器学习课程 CS 22 ...

  9. Machine Learning Algorithms Study Notes(2)--Supervised Learning

    Machine Learning Algorithms Study Notes 高雪松 @雪松Cedro Microsoft MVP 本系列文章是Andrew Ng 在斯坦福的机器学习课程 CS 22 ...

随机推荐

  1. linux下怎样对串口编程

    Linux操作系统从一開始就对串行口提供了非常好的支持,本文就Linux下的串行口通讯编程进行简单的介绍. 串口简单介绍串行口是计算机一种经常使用的接口.具有连接线少.通讯简单.得到广泛的使用. 经常 ...

  2. js ioc 实现

    var ar=[]; var o1={ id:'o1', o2:null } ar.push(o1); var o2={ id:'o2', o1:null } ar.push(o2) var ioc= ...

  3. maven管理整理

    maven管理整理 学习了:https://www.imooc.com/learn/443 mvn -v 版本 compile 编译 test 测试 package 打包 clean 删除 insta ...

  4. haifeng

    [root@localhost 桌面]# yum list|grep wubi ibus-table-chinese-wubi-haifeng.noarch -.el7 base ibus-table ...

  5. .NET Core R2安装及示例教程

    .NET Core R2安装及示例教程 Install for Windows - Visual Studio 2015 1 Download Visual Studio 2015 Make sure ...

  6. lnmp环境网页访问慢排查思路

    1.首先看每个服务器的负载情况 2.若各个服务器负载不高 首先查看是不是负载均衡服务器问题相接访问web服务看是否慢,若也慢则查看是不是访问动态页面慢,创建一个静态页面访问试试,若不慢则是动态页面问题 ...

  7. ARM和STM32的区别及ARM公司架构的发展

    ARM和STM32的区别及ARM公司架构的发展 转:https://www.cnblogs.com/kwdeblog/p/5260348.html ARM是英国的芯片设计公司,其最成功的莫过于32位嵌 ...

  8. PowerDesigner将PDM导出生成WORD文档(转）

    今天的温习老知识,是如何将一个PD设计的PDM来导出WORD文档,这是一个非常实用的功能,可以在软件过程的数据库设计文档编写中节省N多时间, 那不废话了,我们就开始今天的讲解吧! 第一步,点击Repo ...

  9. Java中的Enum的继承

    public interface Icolor{ int apply(int x,int y); } public enum color implements Icolor{ plus("+ ...

  10. request 防盗链

    package request; import java.io.IOException;import javax.servlet.ServletException;import javax.servl ...