The Nature of Statistical Learning Theory

by Vladimir N. Vapnik

The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning from the general point of view 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 general setting of learning problems and the general model of minimizing the risk functional from empirical data - a comprehensive analysis of the empirical risk minimization principle and shows how this allows for the construction of necessary and sufficient conditions for 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 - introducing a new type of universal learning machine that controls the generalization ability.

Genres: Artificial Intelligence, Mathematics, Computer Science, Textbooks, Technology, Academic, Nonfiction

188 pages, Hardcover

First published December 14, 1998

Reviews

[Michiel · Rating 3 out of 5]

Well, it's a book about the mathematical foundation of statistical learning, so it is not an easy read. Gives an interesting overview in the theory behind support vector machines and how they can be applied for classification, regression and density estimation. I liked the philosophical intermezzos.

[Wojciech · Rating 5 out of 5]

An absolute must read for anyone who wants to learn about machine learning and/or artificial intelligence. The very source of the notion of machines "learning", a beautiful, strict, mathematical concept that allowed the whole field to be formed. Even if modern day deep learning goes away from its SLT roots, reading it should be obligatory element to getting a phd in a field.

[Robert · Rating 4 out of 5]

Not light reading :D

I was just looking through this yesterday and thinking how Vapnik's ideas about generalization might still be relevant in thinking about how to develop "Strong AI".

[Harrywaters]

Via justus https://www.kdnuggets.com/2018/04/7-b...