LINGUIST List 9.480

Sat Mar 28 1998

Books: Psycholing, computer & cognitive sciences

Editor for this issue: Anita Huang <anitalinguistlist.org>


Links to the websites of all LINGUIST's supporting publishers are available at the end of this issue.

Directory

  1. Roberta Murphy, The Informational Complexity of Learning

Message 1: The Informational Complexity of Learning

Date: Thu, 19 Mar 1998 15:15:37 -0500
From: Roberta Murphy <rmurphywkap.com>
Subject: The Informational Complexity of Learning

 KLUWER ACADEMIC PUBLISHERS is proud to announce the publication of:
 
 THE INFORMATIONAL COMPLEXITY OF LEARNING:
 Perspectives on Neural Networks and Generative Grammar 
 
 by Partha Niyogi
 Massachusetts Institute of Technology 
 
 Among other topics, THE INFORMATIONAL COMPLEXITY OF LEARNING: 

 Perspectives on Neural Networks and Generative Grammar brings together 
 two important but 
 very different learning problems within the same analytical framework. The 
 first concerns the problem of learning functional mappings using neural 
 networks, followed by learning natural language grammars in the principles 
 and parameters tradition of Chomsky.
 
 These two learning problems are seemingly very different. Neural networks 
 are real-valued, infinite-dimensional, continuous mappings. On the other 
 hand, grammars are boolean-valued, finite-dimensional, discrete (symbolic) 
 mappings. 
 
 The book's objective is to bridge this gap. It uses the formal techniques 
 developed in statistical learning theory and theoretical computer science 
 over the last decade to analyze both kinds of learning problems. Specific 
 results include model selection in neural networks, active learning, 
 language learning and evolutionary models of language change.
 
 THE INFORMATIONAL COMPLEXITY OF LEARNING: Perspectives on Neural Networks 
 and Generative Grammar is a very interdisciplinary work. All individuals 
 interested in the interaction of computer science and cognitive science 
 should enjoy the book. Researchers in artificial intelligence, neural 
 networks, linguistics, theoretical computer science, and statistics will 
 find it particularly relevant.
 
 Contents
 Foreword.
 Preface.
 1. INTRODUCTION.
 2. GENERALIZATION ERROR FOR NEURAL NETS.
 3. ACTIVE LEARNING.
 4. LANGUAGE LEARNING.
 5. LANGUAGE CHANGE.
 6. CONCLUSIONS.
 
 1998 248 pp. ISBN 0-7923-8081-9 $98.00
 
 FOR MORE INFORMATION ABOUT THIS PUBLICATION, PLEASE VISIT OUR On-line 
 Catalogue at: http://www.wkap.nl
 
 or you may order directly from:
 
 Kluwer Academic Publishers
 101 Philip Drive
 Norwell, Ma. 02061
 Phone: 781-871-6600, Fax: (781) 871-6528, E-mail: kluwerwkap.com
 
 Kluwer Academic Publishers
 P. O. Box 322
 3300 AH Dordrecht, The Netherlands
 Phone 31 78 639 2392, Fax: 31 78 6546474, E-mail: serviceswkap.nl
 
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

The following contributing LINGUIST publishers have made their backlists available on the World Wide Web:

1998 Contributors

  • Blackwell Publishers
  • Edinburgh University Press
  • Holland Academic Graphics (HAG)
  • Kluwer Academic Publishers
  • Lawrence Erlbaum Assoc.
  • Oxford University Press
  • Routledge
  • Summer Institute of Linguistics
  • Mouton de Gruyter