《模式识别与机器学习》学习笔记：4.0 线性分类模型：前言

术语

术语	中文含义	备注
decision regions		p179
decision boundaries (decision surfaces)
linearly separable
discriminant function		p180
activation function
link function
generalized linear models

注：#(不确定含义)，*(重点)

4.0 Linear Models for Classification

本小节主要介绍了如下几个内容：

1. 线性分类模型的定义和相关概念

p179, The goal in classification is to take an input vector x and to assign it to one of K discrete classes Ck where k = 1, . . . , K.

分类的目的

 

p179, In this chapter, we consider linear models for classification, by which we mean that the decision surfaces are linear functions of the input vector x and hence are defined by (D − 1)-dimensional hyperplanes within the D-dimensional input space.

本章只讨论了线性分类模型，即决策平面都是输入向量x的线性函数，因此当输入向量的空间维度为D时，决策平面为其空间中的D-1维超平面。

 

p179, Data sets whose classes can be separated exactly by linear decision surfaces are said to be linearly separable.

线性可分数据集的定义。

2. 分类问题的输出变量和上章中回归问题的输出变量的联系和区别

3. 三个常用的分类方法

discriminant function

directly determine the conditional probabilities p(ck|x)

use Bayes’ theorem to determine the conditional probabilities p(ck|x)

4. 回归问题和分类问题的联系和区别

p180, 最后一段内容比较重要

5. 一些算法

 

-------------------------------------------
作者：兔纸张   来源：博客园 ( http://www.cnblogs.com/geiliCode )