Skip to main content
SpringerLink
Log in
Book cover

Dealing with Complexity

A Neural Networks Approach

  • Book
  • © 1998

Overview

Editors:
  1. Mirek Kárný

    1. Institute of Information Theory & Automation, Prague 8, Czech Republic

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  2. Kevin Warwick

    1. Department of Cybernetics, University of Reading, Whiteknights, Reading, UK

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  3. Vera Kůrková

    1. Institute of Computer Science, Academy of Sciences of the Czech Republic, Prague 8, Czech Republic

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

Part of the book series: Perspectives in Neural Computing (PERSPECT.NEURAL)

This is a preview of subscription content, log in via an institution to check access.

Access this book

Log in via an institution
eBook USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

Table of contents (18 chapters)

  1. Front Matter

    Pages I-XV
    Download chapter PDF

  2. Recurrent Neural Networks: Some Systems-Theoretic Aspects

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 1-12

  3. The Use of State Space Control Theory for Analysing Feedforward Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 13-28

  4. Statistical Decision Making and Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 29-46

  5. A Tutorial on the EM Algorithm and Its Applications to Neural Network Learning

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 47-61

  6. On the Effectiveness of Memory-Based Methods in Machine Learning

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 62-75

  7. A Study of Non Mean Square Error Criteria for the Training of Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 76-92

  8. A Priori Information in Network Design

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 93-109

  9. Neurofuzzy Systems Modelling: A Transparent Approach

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 110-125

  10. Feature Selection and Classification by a Modified Model with Latent Structure

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 126-140

  11. Geometric Algebra Based Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 141-157

  12. Discrete Event Complex Systems: Scheduling with Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 158-176

  13. Incremental Approximation by Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 177-188

  14. Approximation of Smooth Functions by Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 189-204

  15. Rates of Approximation in a Feedforward Network Depend on the Type of Computational Unit

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 205-219

  16. Recent Results and Mathematical Methods for Functional Approximation by Neural Networks

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 220-237

  17. Differential Neurocontrol of Multidimensional Systems

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 238-251

  18. The Psychological Limits of Neural Computation

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 252-263

  19. A Brain-Like Design to Learn Optimal Decision Strategies in Complex Environments

    • Mirek Kárný, Kevin Warwick, Vera Kůrková
    Pages 264-303

  20. Back Matter

    Pages 304-308
    Download chapter PDF
Back to top

Keywords

About this book

In almost all areas of science and engineering, the use of computers and microcomputers has, in recent years, transformed entire subject areas. What was not even considered possible a decade or two ago is now not only possible but is also part of everyday practice. As a result, a new approach usually needs to be taken (in order) to get the best out of a situation. What is required is now a computer's eye view of the world. However, all is not rosy in this new world. Humans tend to think in two or three dimensions at most, whereas computers can, without complaint, work in n­ dimensions, where n, in practice, gets bigger and bigger each year. As a result of this, more complex problem solutions are being attempted, whether or not the problems themselves are inherently complex. If information is available, it might as well be used, but what can be done with it? Straightforward, traditional computational solutions to this new problem of complexity can, and usually do, produce very unsatisfactory, unreliable and even unworkable results. Recently however, artificial neural networks, which have been found to be very versatile and powerful when dealing with difficulties such as nonlinearities, multivariate systems and high data content, have shown their strengths in general in dealing with complex problems. This volume brings together a collection of top researchers from around the world, in the field of artificial neural networks.

Editors and Affiliations

  • Institute of Information Theory & Automation, Prague 8, Czech Republic

    Mirek Kárný

  • Department of Cybernetics, University of Reading, Whiteknights, Reading, UK

    Kevin Warwick

  • Institute of Computer Science, Academy of Sciences of the Czech Republic, Prague 8, Czech Republic

    Vera Kůrková

Bibliographic Information

  • Book Title: Dealing with Complexity

  • Book Subtitle: A Neural Networks Approach

  • Editors: Mirek Kárný, Kevin Warwick, Vera Kůrková

  • Series Title: Perspectives in Neural Computing

  • DOI: https://doi.org/10.1007/978-1-4471-1523-6

  • Publisher: Springer London

  • eBook Packages: Springer Book Archive

  • Copyright Information: Springer-Verlag London Limited 1998

  • Softcover ISBN: 978-3-540-76160-0Published: 07 November 1997

  • eBook ISBN: 978-1-4471-1523-6Published: 06 December 2012

  • Series ISSN: 1431-6854

  • Edition Number: 1

  • Number of Pages: XV, 308

  • Number of Illustrations: 5 b/w illustrations

  • Topics: Artificial Intelligence, System Performance and Evaluation

Publish with us

Policies and ethics

Back to top

Search

Navigation