Fr. 40.90

Learning and Categorization in Modular Neural Networks

English · Paperback / Softback

Shipping usually within 3 to 5 weeks

Description

Read more










This book introduces a new neural network model called CALM, for categorization and learning in neural networks. The author demonstrates how this model can learn the word superiority effect for letter recognition, and discusses a series of studies that simulate experiments in implicit and explicit memory, involving normal and amnesic patients. Pathological, but psychologically accurate, behavior is produced by "lesioning" the arousal system of these models. A concise introduction to genetic algorithms, a new computing method based on the biological metaphor of evolution, and a demonstration on how these algorithms can design network architectures with superior performance are included in this volume.

The role of modularity in parallel hardware and software implementations is considered, including transputer networks and a dedicated 400-processor neurocomputer built by the developers of CALM in cooperation with Delft Technical University. Concluding with an evaluation of the psychological and biological plausibility of CALM models, the book offers a general discussion of catastrophic interference, generalization, and representational capacity of modular neural networks. Researchers in cognitive science, neuroscience, computer simulation sciences, parallel computer architectures, and pattern recognition will be interested in this volume, as well as anyone engaged in the study of neural networks, neurocomputers, and neurosimulators.

List of contents

Contents: Part I: CALM: Categorizing and Learning Module. Introduction. Description of CALM. Simulation Studies of Performance and Self-Organization in CALM. Part II: Application. Psychological Models. Pattern Recognition as a Practical Application. Genetic Algorithms: Modularity, Learning, and Network Design. Part III: Revisiting Modularity. Evaluation of CALM. Appendices: Hardware and Software for Neural Networks. Virtual Implementations on Transputer Networks. Hybrid Implementation: the BSP400, a Dedicated Multiprocessor. Physical Implementation: Some Notes on CALM in Analog Hardware. Modular Neurosimulators.

About the author










Authored by Murre, Jacob M.J.

Product details

Authors Jacob M J Murre, Jacob M. J. Murre, Jacob M.J. Murre
Publisher Taylor and Francis
 
Languages English
Product format Paperback / Softback
Released 01.10.1992
 
EAN 9780805813388
ISBN 978-0-8058-1338-8
No. of pages 250
Dimensions 152 mm x 229 mm x 13 mm
Weight 460 g
Subjects Natural sciences, medicine, IT, technology > IT, data processing > IT
Non-fiction book > Psychology, esoterics, spirituality, anthroposophy > Psychology: general, reference works

PSYCHOLOGY / General, Psychology, COMPUTERS / Data Science / Neural Networks, Neural networks and fuzzy systems

Customer reviews

No reviews have been written for this item yet. Write the first review and be helpful to other users when they decide on a purchase.

Write a review

Thumbs up or thumbs down? Write your own review.

For messages to CeDe.ch please use the contact form.

The input fields marked * are obligatory

By submitting this form you agree to our data privacy statement.