Extracting linguistic quantitative rules from supervised neural networks

Authors:
W. Wettayaprasit_affanb;C. Lursinsap;C. H. Chu
Affiliations:
Dept. of Comp. Sci., Fac. of Sci., Prince of Songkla Univ., Songkhla, 90112, Thailand (Correspd. E-mail: wwettayaprasit@yahoo.com) and Adv. Vir. and Intell. Comp. (AVIC) Res. Ctr., Dept. of Math., ...;Advanced Virtual and Intelligent Computing (AVIC) Research Center, Department of Mathematics, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand;The Center for Advanced Computer Studies (CACS), University of Louisiana at Lafayette, Lafayette, LA, 70504, USA
Venue:
International Journal of Knowledge-based and Intelligent Engineering Systems
Year:
2004

Citing 8
Cited 0

Symbolic Representation of Neural Networks

Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Rule extraction by successive regularization

Neural Networks
Using Extra Output Learning to Insert a Symbolic Theory into a Connectionist Network

Minds and Machines
Symbolic Interpretation of Artificial Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Knowledge Discovery by Inductive Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Generalized Analytic Rule Extraction for Feedforward Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Extracting rules from trained neural networks

IEEE Transactions on Neural Networks
Extracting M-of-N rules from trained neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Extracting meaningful and understandable knowledge from a trained neural network is one of the ultimate goals in the area of data mining. In this paper, we propose a technique for extracting knowledge with less complex mathematical elaboration based on our activation interval projection on each dimensional axis with certainty factor refinement. The knowledge is captured in forms of if-then rules, which their premises are the conjunction of input feature intervals representing in linguistic quantities. Our experiment signifies that the extracted rules accurate when compared with those from a neural network.