ML Anthology

Learning Concepts by Synthesizing Minimal Threshold Gate Networks

Arlindo L. Oliveira, Alberto L. Sangiovanni-Vincentelli
ICML 1991 pp. 193-197
doi:10.1016/B978-1-55860-200-7.50042-8 /icml/1991/oliveira1991icml-learning/

Abstract

We propose a new methodology for the synthesis of two-level networks of threshold gates based on techniques related to the ones used in the logic synthesis of digital networks. The proposed approach starts with a large network that performs the desired mapping and reduces its size by applying transformations that preserve the functionality for all examples in the training set.

ICML Semantic Scholar

Cite

Text

Oliveira and Sangiovanni-Vincentelli. "Learning Concepts by Synthesizing Minimal Threshold Gate Networks." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50042-8

Markdown

[Oliveira and Sangiovanni-Vincentelli. "Learning Concepts by Synthesizing Minimal Threshold Gate Networks." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/oliveira1991icml-learning/) doi:10.1016/B978-1-55860-200-7.50042-8

BibTeX

@inproceedings{oliveira1991icml-learning,
  title     = {{Learning Concepts by Synthesizing Minimal Threshold Gate Networks}},
  author    = {Oliveira, Arlindo L. and Sangiovanni-Vincentelli, Alberto L.},
  booktitle = {International Conference on Machine Learning},
  year      = {1991},
  pages     = {193-197},
  doi       = {10.1016/B978-1-55860-200-7.50042-8},
  url       = {https://mlanthology.org/icml/1991/oliveira1991icml-learning/}
}