Using Sampling and Queries to Extract Rules from Trained Neural Networks

This work presents a novel method that casts rule extraction not as a search problem, but instead as a learning problem, and exploits the property that networks can be efficiently queried.

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.