J. Shavlik (1996).
An Overview of Research at Wisconsin on Knowledge-Based Neural Networks. Proceedings of the International Conference on Neural Networks, pp. 65-69, Washington, DC.

This publication is available in PDF and available in postscript.

Abstract:

Recent research at the University of Wisconsin on knowledge-based neural networks is surveyed. This work has focused on (a) using symbolically represented background knowledge to improve neural-network learning and (b) extracting comprehensible symbolic representations from trained networks. Important open issues are discussed.

Return to the publications of the Univ. of Wisconsin Machine Learning Research Group.