Statistical Learning Theory

by Vladimir N. Vapnik

A comprehensive look at learning and generalization theory. The statistical theory of learning and generalization concerns the problem of choosing desired functions on the basis of empirical data. Highly applicable to a variety of computer science and robotics fields, this book offers lucid coverage of the theory as a whole. Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.

Genres: Artificial Intelligence, Science, Mathematics, Academic, Reference

768 pages, Hardcover

First published September 16, 1998

Reviews

[Yan Zhu · Rating 5 out of 5]

This work will become a master piece. However, it didn't get the appreciation it deserves nowadays. Yes this book is full of mathematical equations. However, if u go through the book carefully, u will notice that the author put a lot of efforts on the presentation. Given the topics and the depth covered, the book is very well organized: Big picture is frequently highlighted; deep insights r often shared around with each discussion; the proofs r crystal clean.

To ppl who comments this book as crap, the best response is given by the author himself in Page 684 the last second paragraph! (Don't be afraid, no math there:))

[Leonardo]

Vapnik es el padre de SVM. My respect

[Robert · Rating 4 out of 5]

"The Bible".

Before Deep Learning a lot more people were concerned with Statistical Learning Theory.