DMCA
Using Sampling and Queries to Extract Rules from Trained Neural Networks (1994)
| Venue: | In Proceedings of the Eleventh International Conference on Machine Learning |
| Citations: | 83 - 3 self |
BibTeX
@INPROCEEDINGS{Craven94usingsampling,
author = {Mark W. Craven and Jude W. Shavlik},
title = {Using Sampling and Queries to Extract Rules from Trained Neural Networks},
booktitle = {In Proceedings of the Eleventh International Conference on Machine Learning},
year = {1994},
pages = {37--45},
publisher = {Morgan Kaufmann}
}
Share
 |
 |
 |
 |
||
OpenURL
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. 1 INTRODUCTION A problem that arises when neural networks are used for supervised learning tasks is that, after training, it is usually difficult to understand the concept representations formed by the networks....
Keyphrases
trained neural network neural network rule-extraction approach large assemblage rule extraction m-of-n rule learning problem search problem classification behavior symbolic rule introduction problem conventional search-based approach supervised learning task present experiment novel method real-valued parameter concept representation
