Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems

Fisher, Douglas H.; McKusick, Kathleen B.; Mooney, Raymond J.; Shavlik, Jude W.; Towell, Geoffrey G.

doi:10.1016/B978-1-55860-036-2.50049-7

Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems

Douglas H. Fisher, Kathleen B. McKusick, Raymond J. Mooney, Jude W. Shavlik, Geoffrey G. Towell

ICML 1989 pp. 169-173

doi:10.1016/B978-1-55860-036-2.50049-7 /icml/1989/fisher1989icml-processing/

Abstract

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.

ICML Semantic Scholar

Cite

Text

Fisher et al. "Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems." International Conference on Machine Learning, 1989. doi:10.1016/B978-1-55860-036-2.50049-7

Markdown

[Fisher et al. "Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems." International Conference on Machine Learning, 1989.](https://mlanthology.org/icml/1989/fisher1989icml-processing/) doi:10.1016/B978-1-55860-036-2.50049-7

BibTeX

@inproceedings{fisher1989icml-processing,
  title     = {{Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems}},
  author    = {Fisher, Douglas H. and McKusick, Kathleen B. and Mooney, Raymond J. and Shavlik, Jude W. and Towell, Geoffrey G.},
  booktitle = {International Conference on Machine Learning},
  year      = {1989},
  pages     = {169-173},
  doi       = {10.1016/B978-1-55860-036-2.50049-7},
  url       = {https://mlanthology.org/icml/1989/fisher1989icml-processing/}
}