Designing a Decompositional Rule Extraction Algorithm for Neural Networks
The neural networks are successfully applied to many applications in different domains. However, due to the results made by the neural networks are difficult to explain the decision process of neural networks is supposed as a black box. The explanation of reasoning is important to some applications such like credit approval application and medical diagnosing software. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, a decompositional algorithm is analyzed and designed to extract rules from neural networks. The algorithm is simple but efficient; can reduce the extracted rules but improve the efficiency of the algorithm at the same time. Moreover, the algorithm is compared to the other two algorithms, M-of-N and Garcez, by solving the MONK’s problem.
KeywordsNeural Network Artificial Neural Network Expert System Boolean Logic Decompositional Algorithm
Unable to display preview. Download preview PDF.
- 2.Andrews, R., Geva, S.: Inserting and Extracting Knowledge from Constrained Error Back Propagation Networks. In: Proc. of 6th Australian Conference on Neural Networks, Sydney, NSW (1995)Google Scholar
- 5.Chen, J.C., Liu, T.S., Weng, C.S., Heh, J.S.: An Expert System of Coronary Artery Disease in Chinese and Western Medicine. In: Proc. of 6th Asian-Pacific Conference on Medical and Biological Engineering, Tsukuba, Japan, April 24-27 (2005) PA-3-06Google Scholar
- 6.Craven, M.W., Shavlik, J.W.: Using Sampling and Queries to Extract Rules from Trained Neural Networks. In: Proc. of 11th International Conference on Machine Learning, New Brunswick, pp. 37–45 (1994)Google Scholar
- 7.Freeman, J.A., Skapura, D.M.: Neural Networks. Addison-Wesley, New York (1992)Google Scholar
- 8.Fu, L.M.: Rule Generation from Neural Networks. IEEE Transactions on Systems, Man, and Cybernetics 28(8), 1114–1124 (1994)Google Scholar
- 10.Jackson, P.: Introduction to Expert Systems. Addison-Wesley, New York (1999)Google Scholar
- 12.Pop, E., Hayward, R., Diedrich, A.: RULENEG: Extracting Rules from a Trained Neural Network Using Stepwise Negation. Technical Report, Neurocomputing Research Centre, Queensland University of Technology (1994)Google Scholar
- 16.Thrun, S.B. (ed.): The MONK’s Problems: A Performance Comparison of Different Learning Algorithms. Technical Report CMU-CS-91-197. Carnegie Mellon University (1991)Google Scholar
- 17.Thrun, S.B.: Extracting Provably Correct Rules from Artificial Neural Networks. Technical Report IAI-TR-93-5, Institut für Informatik III. University of Bonn, Germany (1994)Google Scholar
- 19.Towell, G.G., Shavlik, J.W.: The Extraction of Refined Rules from Knowledge-Based Neural Networks. Machine Learning 13, 71–101 (1993)Google Scholar