A Probabilistic Theory of Pattern Recognition

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 me...

Full description

Bibliographic Details
Main Authors: Devroye, Luc, Györfi, Laszlo (Author), Lugosi, Gabor (Author)
Format: eBook
Language:English
Published: New York, NY Springer New York 1996, 1996
Edition:1st ed. 1996
Series:Stochastic Modelling and Applied Probability
Subjects:
Online Access:
Collection: Springer Book Archives -2004 - Collection details see MPG.ReNa
LEADER 01767nmm a2200313 u 4500
001 EB000618269
003 EBX01000000000000000471351
005 00000000000000.0
007 cr|||||||||||||||||||||
008 140122 ||| eng
020 |a 9781461207115 
100 1 |a Devroye, Luc 
245 0 0 |a A Probabilistic Theory of Pattern Recognition  |h Elektronische Ressource  |c by Luc Devroye, Laszlo Györfi, Gabor Lugosi 
250 |a 1st ed. 1996 
260 |a New York, NY  |b Springer New York  |c 1996, 1996 
300 |a XV, 638 p  |b online resource 
653 |a Probability Theory 
653 |a Automated Pattern Recognition 
653 |a Probabilities 
653 |a Pattern recognition systems 
700 1 |a Györfi, Laszlo  |e [author] 
700 1 |a Lugosi, Gabor  |e [author] 
041 0 7 |a eng  |2 ISO 639-2 
989 |b SBA  |a Springer Book Archives -2004 
490 0 |a Stochastic Modelling and Applied Probability 
028 5 0 |a 10.1007/978-1-4612-0711-5 
856 4 0 |u https://doi.org/10.1007/978-1-4612-0711-5?nosfx=y  |x Verlag  |3 Volltext 
082 0 |a 519.2 
520 |a 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