A Probabilistic Theory of Pattern Recognition

  • Luc Devroye
  • László Györfi
  • Gábor Lugosi

Part of the Stochastic Modelling and Applied Probability book series (SMAP, volume 31)

Table of contents

  1. Front Matter
    Pages i-xv
  2. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 1-8
  3. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 9-20
  4. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 21-37
  5. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 39-59
  6. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 61-90
  7. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 91-109
  8. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 111-119
  9. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 121-132
  10. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 133-145
  11. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 147-167
  12. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 169-185
  13. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 187-213
  14. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 215-232
  15. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 233-247
  16. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 249-262
  17. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 263-278
  18. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 279-288
  19. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 289-301
  20. Luc Devroye, László Györfi, Gábor Lugosi
    Pages 303-313

About this book

Introduction

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.

Keywords

Likelihood classification cognition complexity pattern recognition

Authors and affiliations

  • Luc Devroye
    • 1
  • László Györfi
    • 2
  • Gábor Lugosi
    • 2
  1. 1.School of Computer ScienceMcGill UniversityMontrealCanada
  2. 2.Department of Mathematics and Computer ScienceTechnical University of BudapestBudapestHungary

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4612-0711-5
  • Copyright Information Springer-Verlag New York 1996
  • Publisher Name Springer, New York, NY
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4612-6877-2
  • Online ISBN 978-1-4612-0711-5
  • Series Print ISSN 0172-4568
  • Series Online ISSN 2197-439X
  • About this book