A Probabilistic Theory of Pattern Recognition (Stochastic Modelling and Applied Probability)

by: Luc Devroye, Laszlo Györfi, Gabor Lugosi

(20 February 1997)

View FullText article

Amazon.ca, Amazon.de, Amazon.fr, Amazon.co.uk, Amazon.com, WorldCat

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

olivierbousquet, davidr, joeionnojitsu

Find related articles with these CiteULike tags

book, learningtheory, pattern-recognition, probability-theory, statistical-learning-theory

Abstract

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.

@book{dev:gyo:lug96, abstract = {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.}, author = {Devroye, Luc and Gy\"{o}rfi, Laszlo and Lugosi, Gabor }, citeulike-article-id = {134351}, howpublished = {Hardcover}, isbn = {0387946187}, keywords = {book, probability-theory, statistical-learning-theory}, month = {February}, posted-at = {2005-03-31 23:58:45}, priority = {3}, publisher = {Springer}, title = {A Probabilistic Theory of Pattern Recognition (Stochastic Modelling and Applied Probability)}, url = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/0387946187}, year = {1997} }

RIS record

TY - BOOK ID - dev:gyo:lug96 L3 - citeulike-article-id:134351 TI - A Probabilistic Theory of Pattern Recognition (Stochastic Modelling and Applied Probability) PB - Springer SN - 0387946187 N2 - 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. KW - book KW - probability-theory KW - statistical-learning-theory AU - Devroye, Luc AU - Györfi, Laszlo AU - Lugosi, Gabor PY - 1997/02/20/ UR - http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20&path=ASIN/0387946187 ER -

RIS BibTeX