Learning and Generalization

With Applications to Neural Networks

M. Vidyasagar

500 pages, parution le 21/10/2002 (2^eme édition)

Ajouter à une liste

Indisponible

Résumé

How does it differ from first edition? Includes new material on:

support vector machines (SVM's),
fat shattering dimensions
applications to neural network learning,
learning with dependent samples generated by beta-mixing process,
connections between system identification and learning theory
probabilistic solution of "intractable" problems in robust control and matrix theory using randomised algorithms.

In addition, solutions to some open problems posed in the first edition are included, and new open problems are added.
The author is a respected authority in the field of control and systems theory.
This new edition, with substantial new material, takes account of important new developments in the theory of learning. It also deals extensively with the theory of learning control systems, which has now reached a level of maturity comparable to that of learning of neural networks.
The book is written in a manner that would suit self-study and contains comprehensive references. The chapters are also written to be as autonomous as possible and contain updated open problems to enhance further research and self-study.
Contents

Introduction
Preliminaries
Problem Formulations
Vapnik-Chervonenkis, Pseudo- and Fat-Shattering Dimensions
Uniform Convergence of Empirical Means
Learning Under a Fixed Probability Measure
Distribution-Free Learning
Learning Under an Immediate Family of Probabilities
Alternate Models of Learning
Applications to Neural Networks
Applications to Control Systems
Some Open Problems

L'auteur - M. Vidyasagar

Mathukumalli Vidyasagar is currently Executive Vice President in charge of Advanced Technology at Tata Consultancy Services (TCS), India's largest IT firm. Dr. Vidyasagar was formerly the director of the Centre for Artificial Intelligence and Robotics (CAIR), under Government of India's Ministry of Defense.

Caractéristiques techniques

	PAPIER
Éditeur(s)	Springer
Auteur(s)	M. Vidyasagar
Parution	21/10/2002
Édition	2^eme édition
Nb. de pages	500
Format	16 x 24
Couverture	Relié
Poids	1000g
Intérieur	Noir et Blanc
EAN13	9781852333737
ISBN13	978-1-85233-373-7