machine learning(13) -- solving the problem of overfitting:regularization
solving the problem of overfitting:regularization
- 发生的在linear regression上面的overfitting问题
- 发生在logistic regression上面的overfitting
- 怎么解决overfitting
- regularization: cost function of linear regression
- parameters小的话,这样hypothesis就会变得简单,这样就不会overfitting
- 一般不会对θ0进行regularization
- 上式是进行regularization的linear regression的cost function,要使上式的值取最小值
- 对这个cost function 的分析
- 由两个式子(两个目标)组成,第一个式子是为了对trainning data更好的拟合(fitting the training data),第二个式子是为了避免overfitting
- 第二个式子叫regularization term, λ叫regularization parameter, λ是为了平衡两个目标用的
- 如果 λ非常大的话(这时θ1-θn几乎为0,hypothesis变得很简单,只有常数),就会出现underfitting,对trainning data/ new data很低的fitting
- 所以并不是regularization在任何情况下(当 λ非常大的情况下),都能使model更适应new data或者training data
- The regularization term puts a penalty on the cost J,随着模型参数的增多,the penalty increases as well.
machine learning(13) -- solving the problem of overfitting:regularization的更多相关文章
- Solving the Problem of Overfitting
The Problem of Overfitting Cost Function Regularized Linear Regression Note: [8:43 - It is said that ...
- Advice for applying Machine Learning
https://jmetzen.github.io/2015-01-29/ml_advice.html Advice for applying Machine Learning This post i ...
- How do I learn mathematics for machine learning?
https://www.quora.com/How-do-I-learn-mathematics-for-machine-learning How do I learn mathematics f ...
- [C2P2] Andrew Ng - Machine Learning
##Linear Regression with One Variable Linear regression predicts a real-valued output based on an in ...
- Machine Learning - 第3周(Logistic Regression、Regularization)
Logistic regression is a method for classifying data into discrete outcomes. For example, we might u ...
- Course Machine Learning Note
Machine Learning Note Introduction Introduction What is Machine Learning? Two definitions of Machine ...
- 【Machine Learning is Fun!】1.The world’s easiest introduction to Machine Learning
Bigger update: The content of this article is now available as a full-length video course that walks ...
- [C2P1] Andrew Ng - Machine Learning
About this Course Machine learning is the science of getting computers to act without being explicit ...
- Introduction to Machine Learning
Chapter 1 Introduction 1.1 What Is Machine Learning? To solve a problem on a computer, we need an al ...
随机推荐
- Java程序内存分析
1. Runtime.getRuntime().freeMemory() 和 jvisualvm.exe http://blog.csdn.net/u011004037/article/details ...
- Appium移动自动化测试-----(十三)appium API 之其他操作
其它操作针对移动设备上特有的一些操作. 1.熄屏 方法: * lockDevice() 点击电源键熄灭屏幕. 在iOS设备可以设置熄屏一段时间.Android上面不带参数,所以熄屏之后就不会再点亮屏幕 ...
- clang, gcc, gdb
Clang 比 GCC 编译器的优势: 1 编译速度更快 2 编译产出更小 3 出错提示更友好,比如 clang 在编译过程可以直接指出相对简单的出错位置以及它 " 认为 " 正确 ...
- todo----mysql常用语句总结补充完成
todo----mysql常用语句总结补充完成
- STM32之复用功能
复用功能分复用输入,复用输出,STM32芯片内部集成多种模块,如GPIO.串口.i2c等,为使IO端口支持这些模块,厂家对IO端口进行扩展,同一个端口通过设置寄存器会有不同的功能.如下图IO结构图: ...
- Python31之类和对象1(三大特征:多封继——多疯子)
一.对象: Python即是面向对象的编程也是面向过程的编程语言,其内部可谓是无处不对象,我们所熟知的列表,字符串等工厂函数本质上都是对象.对象其实是对属性和方法的封装. 属性是对象的静态特征 方法是 ...
- 基于UDP的编程
前提:基于Linux系统的学习 服务器端编程模型1 socket(2) 创建通讯端点,返回一个文件描述符fd2 bind(2) 将fd绑定到本地的地址和端口while(1){ 阻塞等待客户端请求数据的 ...
- springboot笔记04——读取配置文件+使用slf4j日志
前言 springboot常用的配置文件有yml和properties两种,当然有必要的时候也可以用xml.我个人更加喜欢用yml,所以我在这里使用yml作为例子.yml或properties配置文件 ...
- 一、zuul如何路由到上游服务器
所有文章 https://www.cnblogs.com/lay2017/p/11908715.html 正文 zuul在分布式项目中充当着一个网关的角色,而它最主要的功能像nginx一样针对上游服务 ...
- Java 之 IO 异常的处理【了解】
一.JDK7 前的处理 前面的 Demo 中,一直把异常抛出,而在实际中并不能这样处理,建议使用 try...catch...finally 代码块,处理异常部分. 格式: try{ 可能会产出异常的 ...