Data Classification

Chapter 3

Probabilistic Models for Classification

Hongbo Deng

Yahoo! LabsSunnyvale, CA [e-mail]

Yizhou Sun

College of Computer and Information ScienceNortheastern UniversityBoston, MA [e-mail]

Yi Chang

Yahoo! LabsSunnyvale, CA [e-mail]

Jiawei Han

Department of Computer ScienceUniversity of Illinois at Urbana-ChampaignUrbana, IL [e-mail]

3.1 Introduction

In machine learning, classification is considered an instance of the supervised learning methods, i.e., inferring a function from labeled training data. The training data consist of a set of training examples, where each example is a pair consisting of an input object (typically a vector) x = 〈x1,x2, …,xd 〉 and a desired output value (typically a class label) ...