RGANN: An Efficient Algorithm to Extract Rules from ANNs

TL;DR

This paper introduces RGANN, an efficient algorithm for extracting explicit, understandable, and verifiable symbolic rules from neural networks, improving interpretability without sacrificing accuracy.

Contribution

The paper presents a novel four-phase training algorithm for rule extraction from ANNs, enhancing rule clarity and predictive performance compared to existing methods.

Findings

Generated rules are explicit, understandable, and verifiable.

RGANN achieves comparable or better accuracy than other rule extraction methods.

Experimental results on multiple benchmarks demonstrate good generalization.

Abstract

This paper describes an efficient rule generation algorithm, called rule generation from artificial neural networks (RGANN) to generate symbolic rules from ANNs. Classification rules are sought in many areas from automatic knowledge acquisition to data mining and ANN rule extraction. This is because classification rules possess some attractive features. They are explicit, understandable and verifiable by domain experts, and can be modified, extended and passed on as modular knowledge. A standard three-layer feedforward ANN is the basis of the algorithm. A four-phase training algorithm is proposed for backpropagation learning. Comparing them to the symbolic rules generated by other methods supports explicitness of the generated rules. Generated rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and predictive accuracy. Extensive experimental studies on several benchmarks classification problems, including breast cancer, wine, season, golf-playing, and lenses classification demonstrate the effectiveness of the proposed approach with good generalization ability.