On High-Level Inferencing and the Variable Binding Problem in Connectionist Networks
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.
Unable to display preview. Download preview PDF.
- 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
- Barnden, J. A. (1984). On Short Term Information Processing in Connectionist Theories. Cognition and Brain Theory, 7: 25–59.Google Scholar
- 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
- Hölldobler, S. (1990a). A Connectionist Inference System. International Computer Science Institute. submitted.Google Scholar
- 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
- Pinkas, G. (1990). The Equivalence of Energy Minimization and Propositional Calculus Satisfiability. Technical Report WUCS-90–03, Washington University.Google Scholar
- 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
- 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
- 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