Applications Of Mathematics- A Probabilistic Theory Of Pattern Recognition, Sie

Devroye L.

ISBN 10: 0387946187 / ISBN 13: 9780387946184

Published by Springer, 1996

About this Item

Brand New. Soft Cover International Edition. Different ISBN and Cover Image. Priced lower than the standard editions which is usually intended to make them more affordable for students abroad. The core content of the book is generally the same as the standard edition. The country selling restrictions may be printed on the book but is no problem for the self-use. This Item maybe shipped from US or any other country as we have multiple locations worldwide.

Seller Inventory # ABNR-7342

Bibliographic Details

• Title: Applications Of Mathematics- A Probabilistic Theory Of Pattern Recognition, Sie
• Publisher: Springer
• Publication Date: 1996
• Language: English
• ISBN 10: 0387946187
• ISBN 13: 9780387946184
• Binding: Soft cover
• Edition: International Edition
• Condition: New

About this title

Synopsis

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.

From the Back Cover

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, tree 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.