Interpretation of Artificial Neural Networks: Mapping Knowledge-Based Neural Networks into Rules

Abstract

We propose and empirically evaluate a method for the extraction of expert(cid:173) comprehensible rules from trained neural networks. Our method operates in the context of a three-step process for learning that uses rule-based domain knowledge in combination with neural networks. Empirical tests using real(cid:173) worlds problems from molecular biology show that the rules our method extracts from trained neural networks: closely reproduce the accuracy of the network from which they came, are superior to the rules derived by a learning system that directly refines symbolic rules, and are expert-comprehensible.

Cite

Text

Towell and Shavlik. "Interpretation of Artificial Neural Networks: Mapping Knowledge-Based Neural Networks into Rules." Neural Information Processing Systems, 1991.

Markdown

[Towell and Shavlik. "Interpretation of Artificial Neural Networks: Mapping Knowledge-Based Neural Networks into Rules." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/towell1991neurips-interpretation/)

BibTeX

@inproceedings{towell1991neurips-interpretation,
  title     = {{Interpretation of Artificial Neural Networks: Mapping Knowledge-Based Neural Networks into Rules}},
  author    = {Towell, Geoffrey and Shavlik, Jude W.},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {977-984},
  url       = {https://mlanthology.org/neurips/1991/towell1991neurips-interpretation/}
}