Advertisement

On High-Level Inferencing and the Variable Binding Problem in Connectionist Networks

  • Steffen Hölldobler
Conference paper
Part of the Informatik-Fachberichte book series (INFORMATIK, volume 252)

Abstract

We present a connectionist inference system for Horn logic. The system is based on a unification algorithm for first-order terms and uses Bibel’s connection method. It is restricted in that only one instance of each clause may be used in a proof. But there are no restrictions concerning function symbols or the occurrence of variables. In particular, the inference system handles n-ary function and predicate symbols and multiple occurrences of variables even if these variables are not introduced in the conclusion of a rule. The deductive system has more expressive power than the connectionist high-level inference systems we are aware of. This is elaborated by showing how certain additional restrictions imposed on our system lead to the known inference systems. These additional restrictions are ultimately linked to the way how the variable binding problem is solved.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ballard, D. H. (1986). Parallel Logic Inference and Energy Minimization. In Proceedings of the AAAI National Conference on Artificial Intelligence, pp. 203–208.Google Scholar
  2. Barnden, J. A. (1984). On Short Term Information Processing in Connectionist Theories. Cognition and Brain Theory, 7: 25–59.Google Scholar
  3. Bibel, W. (1987). Automated Theorem Proving. Vieweg Verlag, Braunschweig, second edition.zbMATHGoogle Scholar
  4. Dwork, C., Kannelakis, P. C., Si Mitchell, J. C. (1984). On the Sequential Nature of Unification. Journal of Logic Programming, 1: 35–50.MathSciNetzbMATHCrossRefGoogle Scholar
  5. Feldman, J. A. & Ballard, D. H. (1982). Connectionist Models and Their Properties. Cognitive Science, 6 (3): 205–254.CrossRefGoogle Scholar
  6. Fodor, J. A. & Pylyshyn, Z. W. (1988). Connectionism and Cognitive Architecture: A Critical Analysis. In Pinker & Mehler, eds., Connections and Symbols, pp. 3–71. MIT Press.Google Scholar
  7. Hölldobler, S. (1990a). A Connectionist Inference System. International Computer Science Institute. submitted.Google Scholar
  8. Hölldobler, S. (1990b). A Structured Connectionist Unification Algorithm. In Proceedings of the AAAI National Conference on Artificial Intelligence. (to appear) A long version appeared as Technical Report TR-90–012, International Computer Science Institute, Berkeley, California.Google Scholar
  9. Lange, T. E. & Dyer, M. G. (1989). High-Level Inferencingin a Connectionist Network. Connection Science, 1:181–217.CrossRefGoogle Scholar
  10. Mjolsness, E., Gindi, G., & Anandan, P. (1989). Optimization in Model Matching and Perceptual Organization. Neural Computation, 1: 218–229.CrossRefGoogle Scholar
  11. Pinkas, G. (1990). The Equivalence of Energy Minimization and Propositional Calculus Satisfiability. Technical Report WUCS-90–03, Washington University.Google Scholar
  12. Shastri, L. & Ajjanagadde, V. (1990). From Associations to Systematic Reasoning: A Connectionist Representation of Rules, Variables and Dynamic Bindings. Technical Report MSCIS-90–05, Department of Computer and Information Science, University of Pennsylvania, Philadelphia.Google Scholar
  13. Smolensky, P. (1987). On Variable Binding and the Representation of Symbolic Structures in Connectionist Systems. Technical Report CU-CS-355–87, Department of Computer Science & Institute of Cognitive Science, University of Colorado.Google Scholar
  14. Smolensky, P. (1988). On the Proper Treatment of Connectionism. Behavioral and Brain Sciences, 11: 1–74.CrossRefGoogle Scholar
  15. Stickel, M. E. (1987). An Introduction to Automated Deduction. In Bibel, W. & Jorrand, P., eds., Fundamentals of Artificial Intelligence, pp. 75–132. Springer.Google Scholar
  16. Touretzky, D. S. & Hinton, G. E. (1988). A Distributed Connectionist Production System. Cognitive Science, 12: 423–466.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Steffen Hölldobler
    • 1
    • 2
  1. 1.International Computer Science InstituteBerkeleyUSA
  2. 2.FB InformatikFG IntellektikTH DarmstadtGermany

Personalised recommendations