Rule Extraction Algorithm for Deep Neural Networks: A Review

TL;DR

This review paper discusses various rule extraction algorithms for neural networks, highlighting the limited research specifically focused on rule extraction from deep neural networks and their evaluation based on network structure.

Contribution

It provides a comprehensive review of rule extraction methods, emphasizing the gap in research concerning deep neural networks.

Findings

Limited studies on rule extraction algorithms specifically for DNNs

Classification of algorithms into decompositional, pedagogical, and eclectics

Evaluation of algorithms based on neural network structures

Abstract

Despite the highest classification accuracy in wide varieties of application areas, artificial neural network has one disadvantage. The way this Network comes to a decision is not easily comprehensible. The lack of explanation ability reduces the acceptability of neural network in data mining and decision system. This drawback is the reason why researchers have proposed many rule extraction algorithms to solve the problem. Recently, Deep Neural Network (DNN) is achieving a profound result over the standard neural network for classification and recognition problems. It is a hot machine learning area proven both useful and innovative. This paper has thoroughly reviewed various rule extraction algorithms, considering the classification scheme: decompositional, pedagogical, and eclectics. It also presents the evaluation of these algorithms based on the neural network structure with which the algorithm is intended to work. The main contribution of this review is to show that there is a limited study of rule extraction algorithm from DNN.