A Probabilistic Theory of Pattern Recognition
Authors: Devroye, Luc, Györfi, László, Lugosi, Gábor
Free PreviewBuy this book
- About this Textbook
-
Pattern recognition presents one of the most significant challenges for scientists and engineers, and many different approaches have been proposed. The aim of this book is to provide a self-contained account of probabilistic analysis of these approaches. The book includes a discussion of distance measures, nonparametric methods based on kernels or nearest neighbors, Vapnik-Chervonenkis theory, epsilon entropy, parametric classification, error estimation, free classifiers, and neural networks. Wherever possible, distribution-free properties and inequalities are derived. A substantial portion of the results or the analysis is new. Over 430 problems and exercises complement the material.
- Table of contents (32 chapters)
-
-
Introduction
Pages 1-8
-
The Bayes Error
Pages 9-20
-
Inequalities and Alternate Distance Measures
Pages 21-37
-
Linear Discrimination
Pages 39-59
-
Nearest Neighbor Rules
Pages 61-90
-
Table of contents (32 chapters)
Buy this book

Services for this Book
Recommended for you

Bibliographic Information
- Bibliographic Information
-
- Book Title
- A Probabilistic Theory of Pattern Recognition
- Authors
-
- Luc Devroye
- László Györfi
- Gábor Lugosi
- Series Title
- Stochastic Modelling and Applied Probability
- Series Volume
- 31
- Copyright
- 1996
- Publisher
- Springer-Verlag New York
- Copyright Holder
- Springer Science+Business Media, LLC, part of Springer Nature
- eBook ISBN
- 978-1-4612-0711-5
- DOI
- 10.1007/978-1-4612-0711-5
- Hardcover ISBN
- 978-0-387-94618-4
- Softcover ISBN
- 978-1-4612-6877-2
- Series ISSN
- 0172-4568
- Edition Number
- 1
- Number of Pages
- XV, 638
- Topics