Learning and Generalisation With Applications to Neural Networks

Learning and Generalization provides a formal mathematical theory for addressing intuitive questions such as: • How does a machine learn a new concept on the basis of examples? • How can a neural network, after sufficient training, correctly predict the o

  • PDF / 45,026,794 Bytes
  • 498 Pages / 439 x 666 pts Page_size
  • 42 Downloads / 387 Views

DOWNLOAD

REPORT


Springer-Verlag London Ltd.

Other titles published in this series: Stability and Stabilization ofInfinite Dimensional Systems with Applications Zheng-Hua Luo, Bao-Zhu Guo and Orner Morgul Nonsmooth Mechanics (2nd edition) Bernard Brogliato Nonlinear Control Systems II Alberto Isidori L2-Gain and Passivity Techniques in nonlinear Control Arjan van der Schaft Control ofLinear Systems with Regulation and Input Constraints Ali Saberi, Anton A. Stoorvogel and Peddapullaiah Sannuti Robust and HsoControl BenM. Chen Computer Controlled Systems Efim N. Rosenwasser and Bernhard P. Lampe Dissipative Systems Analysis and Control Rogelio Lozano, Bernard Brogliato, Olav Egeland and Bernhard Maschke Control of Complex and Uncertain Systems Stanislav V. Emelyanov and Sergey K. Korovin Robust Control Design Using H» Methods Ian R.Petersen, Valery A. Ugrinovski and Andrey V. Savkin Model Reduction for Control System Design Goro Obinata and Brian D.O. Anderson Control Theory for Linear Systems Harry 1. Trentelman, Anton Stoorvogel and Malo Hautus Functional Adaptive Control Simon G. Fabri and Visakan Kadirkamanathan Positive ID and 2D Systems Tadeusz Kaczorek Identification and Control Using Volterra Models F.]. Doyle III, R.K. Pearson and B.A. Ogunnaike Non-linear Control for Underactuated Mechanical Systems Isabelle Fantoni and Rogelio Lozano Robust Control (Second edition) ]iirgen Ackermann

M. Vidyasagar

Learning and Generalisation With Applications to Neural Networks With 38 Figures

Springer

M. Vidyasagar, PhD Executive Vice President, Tata Consultancy Services, 1-2-10 Sardar Patel Road, Secunderabad 500 003, India

Series Editors

E.D. Sontag eM. Thoma e A. Isidori e J. van Schuppen

British Library Cataloguing in Publication Data Vidyasagar, M. (Mathukumalli), 1947Learning and generalisation : with applications to neural networks. - 2nd ed. - (Communications and control engineering) 1.Machine learning 2.Neural networks (Computer science) 1.Title 006.3'1 Library of Congress Cataloging-in-Publication Data Vidyasagar, M. (Mathukumalli), 1947Learning and generalisation : with applications to neural networks / M. Vidyasagar.-2nded. p. cm. -- (Communications and control engineering, ISSN 0178-5354) 1. Machine learning. 2. Control theory. 3. Neural networks (Computer science) 1. Title. II. Series. Q325.5 .V53 2002 006.3'1--dc21 2002070674 Apart from any fair dealing for the purposes of research or private study, or criticism or review, as permitted under the Copyright, Designs and Patents Act 1988, this publication may only be reproduced, stored or transmitted, in any form or by any means, with the prior permission in writing of the publishers, or in the case of reprographic reproduction in accordance with the terms oflicences issued by the Copyright Licensing Agency. Enquiries concerning reproduction outside those terms should be sent to the publishers. Communications and Control Engineering Series ISSN 0178-5354 ISBN 978-1-84996-867-6 ISBN 978-1-4471-3748-1 (eBook) DOI 10.1007/978-1-4471-3748-1 © Springer-Verlag London 2003