Using Sampling and Queries to Extract Rules from Trained Neural Networks
Abstract
Concepts learned by neural networks are difficult to understand because they are represented using large assemblages of real-valued parameters. One approach to understanding trained neural networks is to extract symbolic rules that describe their classification behavior. There are several existing rule-extraction approaches that operate by searching for such rules. We present a novel method that casts rule extraction not as a search problem, but instead as a learning problem. In addition to learning from training examples, our method exploits the property that networks can be efficiently queried. We describe algorithms for extracting both conjunctive and M-of-N rules, and present experiments that show that our method is more efficient than conventional search-based approaches.
Cite
Text
Craven and Shavlik. "Using Sampling and Queries to Extract Rules from Trained Neural Networks." International Conference on Machine Learning, 1994. doi:10.1016/B978-1-55860-335-6.50013-1Markdown
[Craven and Shavlik. "Using Sampling and Queries to Extract Rules from Trained Neural Networks." International Conference on Machine Learning, 1994.](https://mlanthology.org/icml/1994/craven1994icml-using/) doi:10.1016/B978-1-55860-335-6.50013-1BibTeX
@inproceedings{craven1994icml-using,
title = {{Using Sampling and Queries to Extract Rules from Trained Neural Networks}},
author = {Craven, Mark W. and Shavlik, Jude W.},
booktitle = {International Conference on Machine Learning},
year = {1994},
pages = {37-45},
doi = {10.1016/B978-1-55860-335-6.50013-1},
url = {https://mlanthology.org/icml/1994/craven1994icml-using/}
}