219775

9780387987804

Nature of Statistical Learning Theory
Nature of Statistical Learning Theory
$128.62
$3.95 Shipping
  • Condition: New
  • Provider: Ergodebooks Contact
  • Provider Rating:
    83%
  • Ships From: Multiple Locations
  • Shipping: Standard
  • Comments: Buy with confidence. Excellent Customer Service & Return policy. Ships Fast. 24*7 Customer Service.

   30-day money back guarantee
$117.46
$3.95 Shipping
  • Condition: Good
  • Provider: Ergodebooks Contact
  • Provider Rating:
    83%
  • Ships From: Multiple Locations
  • Shipping: Standard
  • Comments: Buy with confidence. Excellent Customer Service & Return policy. Ships Fast. 24*7 Customer Service.

   30-day money back guarantee

Ask the provider about this item.

Most renters respond to questions in 48 hours or less.
The response will be emailed to you.
Cancel
  • ISBN-13: 9780387987804
  • ISBN: 0387987800
  • Edition: 2
  • Publication Date: 1999
  • Publisher: Springer

AUTHOR

Vapnik, Vladimir N.

SUMMARY

The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning as a general problem of function estimation based on empirical data. Omitting proofs and technical details, the author concentrates on discussing the main results of learning theory and their connections to fundamental problems in statistics. These include:* the setting of learning problems based on the model of minimizing the risk functional from empirical data* a comprehensive analysis of the empirical risk minimization principle including necessary and sufficient conditions for its consistency* non-asymptotic bounds for the risk achieved using the empirical risk minimization principle* principles for controlling the generalization ability of learning machines using small sample sizes based on these bounds* the Support Vector methods that control the generalization ability when estimating function using small sample size.The second edition of the book contains three new chapters devoted to further development of the learning theory and SVM techniques. These include:* the theory of direct method of learning based on solving multidimensional integral equations for density, conditional probability, and conditional density estimation* a new inductive principle of learning.Written in a readable and concise style, the book is intended for statisticians, mathematicians, physicists, and computer scientists.Vladimir N. Vapnik is Technology Leader AT&T Labs-Research and Professor of London University. He is one of the founders of statistical learning theory, and the author of seven books published in English, Russian, German, and Chinese.Vapnik, Vladimir N. is the author of 'Nature of Statistical Learning Theory', published 1999 under ISBN 9780387987804 and ISBN 0387987800.

[read more]

Questions about purchases?

You can find lots of answers to common customer questions in our FAQs

View a detailed breakdown of our shipping prices

Learn about our return policy

Still need help? Feel free to contact us

View college textbooks by subject
and top textbooks for college

The ValoreBooks Guarantee

The ValoreBooks Guarantee

With our dedicated customer support team, 30-day no-questions-asked return policy, and our price match guarantee, you can rest easy knowing that we're doing everything we can to save you time, money, and stress.