April 2015
Intermediate to advanced
1062 pages
40h 35m
English
The goal of this chapter is to present some of the more classical techniques for classification. These methods is a must for any newcomer in the field. Bayesian decision theory is first reviewed and the concepts of discriminant functions and decision surfaces are introduced. Then, minimum distance classifiers are presented as a special instance of the Bayesian classification. The naive Bayes classifier is discussed and the design of linear models for classification are presented, including logistic regression and Fisher’s linear discriminant method. Then, decision trees are introduced. The technique of combining classifiers is discussed, and the Adaboost algorithm and the method of ...