Addressing Knowledge-Representation Issues in Connectionist Symbolic Rule Encoding for General Inference
This chapter describes one method for addressing knowledge representation issues that arise when a connectionist system replicates a standard symbolic style of inference for general inference. Symbolic rules are encoded into the networks, called structured predicate networks (SPN) using neuron-like elements. Knowledge-representation issues such as unification and consistency checking between two groups of unifying arguments arise when a chain of inference is formed over the networks encoding special type of symbol rules. These issues are addressed by connectionist sub-mechanisms embedded into the networks. As a result, the proposed SPN architecture is able to translate a significant subset of first-order Horn Clause expressions into a connectionist representation that may be executed very efficiently.
KeywordsConsistency Check Binding Interaction Oscillation Cycle Variable Binding Variable Argument
Unable to display preview. Download preview PDF.
- 4.Barnden, J.: Neural-net implementation of complex symbol-processing in a mental model approach to syllogistic reasoning. In: Proceedings of The 11th International Joint Conference on Artificial Intelligence, pp. 568–573. Morgan Kaufmann Publishers Inc, San Mateo (1989)Google Scholar
- 5.Hölldobler, S.H., Kurfeβ, F.: CHCL - A connectionist inference system. In: Fronhöfer, B., Wrightson, G. (eds.) Parallelization in Inference Systems. LNCS, vol. 342, pp. 318–342. Springer, Berlin (1991)Google Scholar
- 7.Shastri, L., Ajjanagadde, V.: From simple associations to systematic reasoning: A connectionist representation of rules. variables, and dynamic bindings using temporal synchrony. Behavioral and Brain Sciences 16(3), 417–451 (1993)Google Scholar
- 9.Park, N.S., Robertson, D.: A connectionist representation of symbolic components, dynamic bindings and basic inference operations. In: Proceeding of ECAI 1996 Workshop on Neural Networks and Structured Knowledge, pp. 33–39 (1996)Google Scholar
- 10.Park, N.S., Robertson, D.: A localist network architecture for logical inference. In: Sun, R., Alexandre, F. (eds.) Connectionist-Symbolic Integration. Lawrence Erlbaum Associates Publishers, Hillsdale (1997)Google Scholar
- 11.Park, N.S.: A Connectionist Representation of First-Order Formulae with Dynamic Variable Binding, Ph.D. dissertation, Department of Artificial Intelligence, University of Edinburgh (1997)Google Scholar
- 13.Hölldobler, S.H.: A structured connectionist unification algorithm. In: Proceedings of the National Conference on Artificial intelligence, pp. 587–593. AAAI Press, Menlo Park (1990)Google Scholar