Knowledge-Based Neurocomputing

Edited by Ian Cloete and J M. Zurada
Overview

Neurocomputing methods are loosely based on a model of the brain as a network of simple interconnected processing elements corresponding to neurons. These methods derive their power from the collective processing of artificial neurons, the chief advantage being that such systems can learn and adapt to a changing environment. In knowledge-based neurocomputing, the emphasis is on the use and representation of knowledge about an application. Explicit modeling of the knowledge represented by such a system remains a major research topic. The reason is that humans find it difficult to interpret the numeric representation of a neural network.

The key assumption of knowledge-based neurocomputing is that knowledge is obtainable from, or can be represented by, a neurocomputing system in a form that humans can understand. That is, the knowledge embedded in the neurocomputing system can also be represented in a symbolic or well-structured form, such as Boolean functions, automata, rules, or other familiar ways. The focus of knowledge-based computing is on methods to encode prior knowledge and to extract, refine, and revise knowledge within a neurocomputing system.

Contributors: C. Aldrich, J. Cervenka, I. Cloete, R.A. Cozzio, R. Drossu, J. Fletcher, C.L. Giles, F.S. Gouws, M. Hilario, M. Ishikawa, A. Lozowski, Z. Obradovic, C.W. Omlin, M. Riedmiller, P. Romero, G.P.J. Schmitz, J. Sima, A. Sperduti, M. Spott, J. Weisbrod, J.M. Zurada.

Table of Contents

  1. Preface and Acknowledgements
  2. Contributors
  3. 1. Knowledge-Base Neurocomputing: Past, Present, and Future

    Ian Cloete

  4. 2. Architectures and Techniques for Knowledge-Based Neurocomputing

    Melanie Hilario

  5. 3. Symbolic Knowledge Representation in Recurrent Neural Networks: Insights from Theoretical Models of Computation

    Christian W. Omlin and C. Lee Giles

  6. 4. A Tutorial on Neurocomputing of Structures

    Alessandro Sperduti

  7. 5. Structural Learning and Rule Discovery

    Masumi Ishikawa

  8. 6. VLANN: Transformation of Rules to Artificial Neural Networks

    Ian Cloete

  9. 7. Integration of Heterogeneous Sources of Partial Domain Knowledge

    Pedro Romero, Zoran Obradović and Justin Fletcher

  10. 8. Approximation of Differential Equations Using Neural Networks

    Rico A. Cozzio

  11. 9. Fynesse: A Hybrid Architecture for Self-Learning Control

    Martin Riedmiller, Martin Spott and Joachim Weisbrod

  12. 10. Data Mining Techniques for Designing Neural Network Time Series Predictors

    Radu Drossu and zoran Obradović

  13. 11. Extraction of Decision Trees from Artificial Neural Networks

    Gregor Schmitz, Chris Aldrich and Francois Gouws

  14. 12. Extraction of Linguistic Rules from Data via Neural Networks and Fuzzy Approximation

    Andrzej Lozowski and Jacek M. Zurada

  15. 13. Neural Knowledge Processing in Expert Systems

    Jiří Šíma and Jiří Červenka

  16. Index