Proceedings of the International Symposium on Integrating Knowledge and Neural Heuristics 1994 (ISIKNH-94), pp. 75-85, Pensacola, FL, May 1994.
Paper ID: 33
Category: Theory and Knowledge Refinedment, Uncertain Reasoning, Neural-Network Learning
This paper describes RAPTURE --- a system for revising probabilistic rule bases that converts symbolic rules into a connectionist network, which is then trained via connectionist techniques. It uses a modified version of backpropagation to refine the certainty factors of the rule base, and uses ID3's information-gain heuristic (Quinlan) to add new rules. Work is currently under way for finding improved techniques for modifying network architectures that include adding hidden units using the UPSTART algorithm (Frean). A case is made via comparison with fully connected connectionist techniques for keeping the rule base as close to the original as possible, adding new input units only as needed.
