M. Craven & J. Shavlik (1993).
Learning Symbolic Rules Using Artificial Neural Networks. Proceedings of the Tenth International Conference on Machine Learning, pp. 73-80, Amherst, MA. Morgan Kaufmann.
This publication is available in PDF and available in postscript.
A distinct advantage of symbolic learning algorithms over artificial neural networks is that typically the concept representations they form are more easily understood by humans. One approach to understanding the representations formed by neural networks is to extract symbolic rules from trained networks. In this paper we describe and investigate an approach for extracting rules from networks that uses (1) the NofM extraction algorithm, and (2) the network training method of soft weight-sharing. Previously, the NofM algorithm had been successfully applied only to knowledge-based neural networks. Our experiments demonstrate that our extracted rules generalize better than rules learned using the C4.5 system. In addition to being accurate, our extracted rules are also reasonably comprehensible.
Computer Sciences Department
College of Letters and Science
University of Wisconsin - Madison
INFORMATION ~ PEOPLE ~ GRADS ~ UNDERGRADS ~ RESEARCH ~ RESOURCES
5355a Computer Sciences and Statistics ~ 1210 West Dayton Street, Madison, WI 53706
firstname.lastname@example.org ~ voice: 608-262-1204 ~ fax: 608-262-9777