Combining a Connectionist Type Hierarchy With a Connectionist Rule-Based Reasoner

This paper describes an efficient connectionist knowledge representation and reasoning system that combines rule-based reasoning with reasoning about inheritance and classification within an IS-A hierarchy. In addition to a type hierarchy, the proposed system can encode generic facts such as 'Cats prey on birds' and rules such a s 'if z preys on y then y is scared of z ' and use them to infer that Tweety (who is a Canary) is scared of Sylvestor (who is a Cat). The system can also encode qualified rules such as 'if an animate agent walks into a solid object then the agent gets hurt'. The proposed system can answer queries in time that is only proportional to the length of the shortest derivation of the query and is independent of the sire of the knowledge base. The system maintains and propagates variable bindings using temporally synchronous i.e., in-phase firing of appropriate nodes. *This work was supported by NSF grant IRI 8805465 and ARO grant ARO-DAA2984-9-0027.