Rule Extraction from Trained Neural Network with Evolutionary Algorithms
This paper describes a solution to the problem of incomprehensibility of the neural network by introducing simultaneously working Evolutionary Algorithms as a tool for extracting set of rules in the form of if — then. Each Evolutionary Algorithm is working for searching rules describing one class, which is recognized by a Neural Network. The proposed method has been tested on real domains in order to analyze its behavior under various conditions. A comparison with other rule extraction methods is presented as well.
KeywordsNeural Network Artificial Neural Network Evolutionary Algorithm Crossover Operator Input Pattern
Unable to display preview. Download preview PDF.
- 2.Andrews, R.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge—Based Systems, Volume: 8, Issue: 6, December, (1995) 373–389Google Scholar
- 3.Fu L., M.: Rule Generation from neural network. IEEE Transactions on Systems, M.n and Cybernetics vol. 24, No. 8. August (1994) 1114–1124Google Scholar
- 4.Setiono, R.: Extracting rules from pruned neural networks for breast cancer diagnosis. Artificial Intelligence in Medicine, Volume: 8, Issue: 1, February, (1996) 37–51Google Scholar
- 5.Taha, I., Gosh, J.: Symbolic interpretation of artificial neural networks, Tech. Report TR–97–01–106, the Computer and Vision Research Center, University of Texas, Austin, 1996.Google Scholar
- 6.Thrun, S.: Extracting rules from artificial neural networks with distributed representation. Proceedings of the Eleventh International Conference on Machine Learning, New Brunswick, NJ. Morgan KaufmanGoogle Scholar
- 7.Tickle, A., Orlowski, M., Diedrich, J.: A methodology for extracting rules from trained neural networks. Rules and Networks: Proceedings of the Rule Extraction From Trained Artificial Neural Networks Workshop, Queensland University of Technology, Neurocomputing Research Center QUT NRC, April (1996) 90–102Google Scholar