SVM和logistics笔记
2016-04-13 23:26
295 查看
SVM的参数选择:
C(1/lambda):Large C: lower bias,high variance
small C,Higher bias, low variance
sigma^2: Large sigma^2: Feature fi, vary more smoothly
Higher bias, lower variance
small sigma^2: Feature fi vary loss less smoothly
Lower bias, higher variance
SVM 和Logistics回归的比较
n=number of features, m=number of training examples
if n is large(relative to m): e.g. n>=m, n=10000, m=10...1000
Use logistic regression, or SVM without a kernel("linear kernel")
if n is small, m is intermediate (n=1000, m=10-10000)
Use SVM with Gaussian kernel
if n is small, m is large
Create/add more features, then use logistic regression or SVM without a kernel
Neural network likely to work well for most of these settings, but may be slower to train
C(1/lambda):Large C: lower bias,high variance
small C,Higher bias, low variance
sigma^2: Large sigma^2: Feature fi, vary more smoothly
Higher bias, lower variance
small sigma^2: Feature fi vary loss less smoothly
Lower bias, higher variance
SVM 和Logistics回归的比较
n=number of features, m=number of training examples
if n is large(relative to m): e.g. n>=m, n=10000, m=10...1000
Use logistic regression, or SVM without a kernel("linear kernel")
if n is small, m is intermediate (n=1000, m=10-10000)
Use SVM with Gaussian kernel
if n is small, m is large
Create/add more features, then use logistic regression or SVM without a kernel
Neural network likely to work well for most of these settings, but may be slower to train
相关文章推荐
- struts1进行多文件的上传
- 读书笔记--C语言接口与实现--异常和断言
- MSP432学习笔记--如何在IAR环境下新建工程
- 技术转团队管理(项目经理)的感受
- jQuery.lazyload详解
- 运行APP时dex2oat过程中DumpLIRInsn函数出错
- hihoCoder 1043 完全背包
- iOS有关横向TableView的东西
- jQuery.lazyload详解
- PSP(4.6——4.12)以及周记录
- iOS instruments介绍
- poj 1118 Lining Up
- 我是一个线程
- SIP:用Riverbank的SIP创建C++库的Python模块(把自己的C++库包装成Python模块)
- Python命令Tab自动补全脚本
- 嵌入式操作系统基础知识(二)
- Dreaming
- 关于UICollectionView的headerView的问题
- Leetcode #42. Trapping Rain Water 雨水收集 解题报告
- Python学习路程day11