Picture 1 of 1

The Nature of Statistical Learning Theory by Vladimir Vapnik (Hardcover, 1999)

Buchpark (82083)

98.2% positive Feedback

Price:

£109.60

Free postage

Estimated delivery Fri, 13 Jun - Fri, 20 Jun

Returns:

30 days return. Buyer pays for return postage. If you use an eBay delivery label, it will be deducted from your refund amount.

Condition:

Very Good

In rare cases, a book may differ from the stated edition. Each item is manually inspected and evaluated by us. Very Good Used item in very good condition. Item is in used but good condition. It may be a defect copy in good condition.

About this product

Product Information

The aim of this text 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 connection 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; an 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; princples for controlling the generalization ability of learning machines using small sample sizes; and introducing a new type of universal learning machine that controls the generalization ability.