Learning Kernel Classifiers

Theory and algorithms

Ralf Herbrich

364 pages, parution le 30/09/2002

Ajouter à une liste

Indisponible

Résumé

Linear classifiers in kernel spaces have emerged as a major topic within the field of machine learning. The kernel technique takes the linear classifier--a limited, but well-established and comprehensively studied model--and extends its applicability to a wide range of nonlinear pattern-recognition tasks such as natural language processing, machine vision, and biological sequence analysis.
This book provides the first comprehensive overview of both the theory and algorithms of kernel classifiers, including the most recent developments. It begins by describing the major algorithmic advances: kernel perceptron learning, kernel Fisher discriminants, support vector machines, relevance vector machines, Gaussian processes, and Bayes point machines. Then follows a detailed introduction to learning theory, including VC and PAC-Bayesian theory, data-dependent structural risk minimization, and compression bounds.
Throughout, the book emphasizes the interaction between theory and algorithms: how learning algorithms work and why. The book includes many examples, complete pseudo code of the algorithms presented, and an extensive source code library.

Contents

1 Introduction
I Learning Algorithms
2 Kernel Classifiers from a Machine Learning Perspective
3 Kernel Classifiers from a Bayesian Perspective
II Learning Theory
4 Mathematical Models of Learning
5 Bounds for Specific Algorithms
III Appendices
A Theoretical Background and Basic Inequalities
B Proofs and Derivations - Part I
C Proofs and Derivations - Part II
D Pseudocodes 321
List of Symbols 331
References 339
Index 357

Caractéristiques techniques

	PAPIER
Éditeur(s)	The MIT Press
Auteur(s)	Ralf Herbrich
Parution	30/09/2002
Nb. de pages	364
Format	18,5 x 23,5
Couverture	Relié
Poids	870g
Intérieur	Noir et Blanc
EAN13	9780262083065
ISBN13	978-0-262-08306-5