ML Anthology

Rule Representations in a Connectionist Chunker

David S. Touretzky, Gillette Elvgreen Iii
NeurIPS 1989 pp. 431-438
/neurips/1989/touretzky1989neurips-rule/

Abstract

We present two connectionist architectures for chunking of symbolic rewrite rules. One uses backpropagation learning, the other competitive learning. Although they were developed for chunking the same sorts of rules, the two differ in their representational abilities and learning behaviors.

PDF NeurIPS Semantic Scholar

Cite

Text

Touretzky and Iii. "Rule Representations in a Connectionist Chunker." Neural Information Processing Systems, 1989.

Markdown

[Touretzky and Iii. "Rule Representations in a Connectionist Chunker." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/touretzky1989neurips-rule/)

BibTeX

@inproceedings{touretzky1989neurips-rule,
  title     = {{Rule Representations in a Connectionist Chunker}},
  author    = {Touretzky, David S. and Iii, Gillette Elvgreen},
  booktitle = {Neural Information Processing Systems},
  year      = {1989},
  pages     = {431-438},
  url       = {https://mlanthology.org/neurips/1989/touretzky1989neurips-rule/}
}