机器学习基石-09-4-Linear Regression for Binary Classification
2017-11-06 23:07
465 查看
把{-1,+1}看做是实数的一种,然后对{-1,+1}使用linear regression得到了一个w,这个w会使得在+1的地方告诉我是一个>0的事情,在-1的地方告诉<0的事情。
fun time
A,B,C都在error 0/1的上面,y=+1和y=-1两种情况的图形都是在error 0/1的上方,ABC三个选项是以后会用到的很重要的error measure的方法。
squared error就是一个二次函数,是抛物线。
相关文章推荐
- 【Linear Models for Binary Classification】林轩田机器学习基石
- 机器学习基石-09-1-Linear Regression Problem
- 机器学习基石-09-2-Linear Regression Algorithm
- 9-4-Linear Regression for Binary Classification
- 9. 机器学习基石-How can Machine Learn? - Linear Model for Classification
- 台湾大学林轩田机器学习基石课程学习笔记11 -- Linear Models for Classification
- 机器学习基石---Linear Models for Classification
- Coursera台大机器学习课程笔记10 -- Linear Models for Classification
- 林轩田机器学习基石心得11:Linear Models for Classification
- 2 - 7 - Gradient Descent For Linear Regression (10 min)
- linear model for classification
- 第三章:linear models for regression exericse 1-7
- Optimal linear combination of neural networks for improving classification performance 概述
- Stanford机器学习---第一讲. Linear Regression with one variable
- 机器学习-Linear Regression with One Variable
- 斯坦福机器学习视频笔记 Week1 线性回归和梯度下降 Linear Regression and Gradient Descent
- [机器学习实验2]Multivariate Linear Regression
- Stanford公开课机器学习---week1-2.单变量线性回归(Linear Regression with One Variable)
- 关于2010_CVPR_Locality-constrained Linear Coding for Image Classification