Skip to main content
Article
Rule Extraction Algorithm for Deep Neural Networks: A Review
International Journal of Computer Science and Information Security (IJCSIS) (2016)
  • Tameru Hailesilassie, National University of Science and Technology (MISiS) Moscow,Russia
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.
Keywords
  • Artificial neural network; Deep neural network; Rule extraction; Decompositional; Pedagogical; Eclectic.
Publication Date
Summer August 15, 2016
Publisher Statement
International Journal of Computer Science and Information Security (IJCSIS),
Vol. 14, No. 7, July 2016, https://sites.google.com/site/ijcsis/
ISSN 1947-5500
Citation Information
Tameru Hailesilassie. "Rule Extraction Algorithm for Deep Neural Networks: A Review" International Journal of Computer Science and Information Security (IJCSIS) Vol. 14, No. 7 (2016) p. 376 - 381 ISSN: 1947-5500
Available at: http://works.bepress.com/tameru-hailesilassie/1/