The Intl Symposium on Integrating Knowledge and Neural

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 modi ed version of backpropagation to re ne the certainty factors of the rule base, and uses ID3's information-gain heuristic (Quinlan, 1986) to add new rules. Work is currently under way for nding improved techniques for modifying network architectures that include adding hidden units using the UPSTART algorithm (Frean, 1990). 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.