Symbolic Learning in Connectionist Production Systems

  • Wolfgang Eppler
Conference paper


The paper discusses an approach to combine classical artificial intelligence with connectionism. The crucial point with this intention is the implementation of symbols in neural networks. Several proposals are mentioned in [2]. The next important thing to be examined is the increase or modification of knowledge in a connectionist system. In this paper two types of learning are introduced: subsymbolic learning by experience and symbolic learning from linguistic rules. Symbolic learning requires two regions of processing, the language region and the signal region, both of them being coupled with associative links. Symbolic rules are processed sequentially in several cycles, and affect mainly the language region by also influencing the signal region, whereas subsymbolic rules are local to each of the regions and their consequences can be concluded in parallel. In a combined system with both kinds of rules subsymbolic learning and subsymbolic rules are the basis for symbolic learning and the application of linguistic rules. First results with a prototype system are introduced.


Signal Region Versus Versus Versus Combine System Versus Versus Versus Versus Versus Versus Versus Versus Versus 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Deffuant, G., Dualite local/global & Algorithmes de recrutement, in Proceedings of the Neuro-Nimes’ 90 (ed. J. Herault), EC2 1990, pp. 147-159Google Scholar
  2. [2]
    Eppler, W., Prestructuring of neural networks with fuzzy rules, in Proceedings of the Neuro-Nimes’ 90 (ed. J. Herault), EC2 1990, pp. 227-241Google Scholar
  3. [3]
    Eppler, W., Implementation of Fuzzy Production Systems with Neural Networks, in R. Eckmiller et al. (Ed.) Parallel Processing in Neural Systems and Computers, North Holland, 1990, pp. 249–252Google Scholar
  4. [4]
    Eppler, W., Verarbeitung von Symbolen in Neuronalen Netzen, in Güsgen, H.W. et al., Massive Parallelität und Inferenz, Forschungsbericht AIDA-91-16, 1991, pp. 13-16Google Scholar
  5. [5]
    Habel, C., Pribbenov, S., Zum Verstehen räumlicher Ausdrücke des Deutschen — Transitivität räumlicher Relationen, in Brauer/ Freksa (ed.): Wissensbasierte Systeme, Informatik-Fachberichte 227, 1989, pp. 139–152Google Scholar
  6. [6]
    Kosslyn, S., Image and Mind. Harvard UP, Cambridge, Mass., 1980Google Scholar
  7. [7]
    Smolensky, P., Tensor product variable binding and the representation of symbolic structures in connectionist systems, in Artificial Intelligence Vol.46, 1990, pp. 159–216MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1993

Authors and Affiliations

  • Wolfgang Eppler
    • 1
  1. 1.Institut für Rechnerentwurf und FehlertoleranzUniversität Karlsruhe, FZIKarlsruheGermany

Personalised recommendations