Symbolic and connectionist learning strategies are receiving much attention. Comparative studies should qualify the advantages of systems from each paradigm. However, these systems make differing assumptions along several dimensions, thus complicating the design of 'fair' experimental comparisons. This paper describes our comparative studies of ID3 and back-propagation and suggests experimental dimensions that may be useful in cross-paradigm experimental design.

PDF

In Proceedings of the Sixth International Workshop on Machine Learning, pp. 169--173, Ithaca, New York 1989.

@inproceedings{fisher:ml89, title={Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems}, author={Douglas Fisher and Kathleen McKusick and Raymond J. Mooney and Jude W. Shavlik and Geoffrey Towell}, booktitle={Proceedings of the Sixth International Workshop on Machine Learning}, address={Ithaca, New York}, pages={169--173}, url="http://www.cs.utexas.edu/users/ai-lab?fisher:ml89", year={1989} }