Rule Extraction Algorithm for Deep Neural Networks: A Review
This is an incremental review that identifies gaps in making DNNs more acceptable for data mining and decision systems by improving their explainability.
The paper reviews rule extraction algorithms for deep neural networks (DNNs) to address their lack of interpretability, highlighting that there is limited research on extracting rules from DNNs despite their high accuracy.
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.