Abstract
We have developed a fuzzy neural expert system that has the precision and learning ability of a neural network. Knowledge is acquired from domain experts as fuzzy rules and membership functions. Then, they are converted into a neural network which implements fuzzy inference without rule matching. The neural network is applied to problem-solving and learns from the data obtained during operation to enhance the accuracy. The learning ability of the neural network makes it easy to modify the membership functions defined by domain experts. Also, by modifying the weights of neural networks adaptively, the problem of belief propagation in conventional expert systems can be solved easily. Converting the neural network back into fuzzy rules and membership functions helps explain the inner representation and operation of the neural network.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Wang Shijun, Shan Yuqiu, Wang Shulin. Research and design of a multi-level interpretation expert system. InProceedings of the Third International Conference on Computers for Young Scientists, Beijing, 1993.
Kawamura A, Watanabe N, Okada H, Asakawa K. A prototype of neuro-fuzzy cooperation system. InProceedings of the International Conference on Fuzzy Logic & Neural Networks, U.S.A., 1992, pp. 1284–1291.
Rumelhart D Eet al. Learning internal representation by error propagation. Parellel distributed processing in the microstructures of cognition. MIT Press, 1986.
Zadel L A. The role of fuzzy logic in the management of uncertainty in expert systems. Approximate Reasoning in Expert Systems, Gupta M M, Knadel A, Bandler W, Kiszka F B (eds.), 1985.
Lin C T, Lee C S G. Real-time supervised structure/parameter learning for fuzzy neural network. InProceedings of the International Conference on Fuzzy Logic & Neural Networks, U.S.A., 1992, pp. 1284–1291.
Author information
Authors and Affiliations
Additional information
Wang Shijun received his B.S. degree from Mathematics Department of Heilongjiang University in 1983, his M.S. and Ph.D. degrees from Institute of Computing Technology, The Chinese Academy of Sciences, in 1991 and 1994 respectively. Now he is the post-doctor of The Institute of Computer Science and Technology, Beijing University. His research interests cover the architectures and methods of the hybrid systems and geographic information systems (GIS).
Wang Shulin is a Professor of The Institute of Computing Technology, The Chinese Academy of Sciences. He once worked in the Computing Center, The Chinese Academy of Sciences, USSR. He has done research upon artificial intelligence, expert system, and computer application. He is now the Director of China Artificial Intelligence in Education Society, the vice Director and General Secretary of China Artificial Intelligence Association, and the Director of Professional Committee of Open Systems, CCF.
Rights and permissions
About this article
Cite this article
Wang, S., Wang, S. Research and design of a fuzzy neural expert system. J. of Comput. Sci. & Technol. 10, 112–123 (1995). https://doi.org/10.1007/BF02948421
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02948421