Abstract
Often a major difficulty in the design of rule-based expert systems is the process of acquiring the requisite knowledge in the form of production rules. In most of expert systems, crisp or fuzzy if-then rules are generally derived from human experts using linguistic information. However, the initial linguistic rules are invariably rather crude and, although qualitatively correct, need to be refined to achieve better performance. In this paper, we present an innovative approach to the rule extraction directly from experimental numerical data for pattern recognition and system identification. This paper presents a neural network-based system which is trained in such a way that it provides an appealing solution to the problem of knowledge acquisition based on experimental numerical data. The values of the network's parameters, after sufficient training, are then utilized to generate both crisp and fuzzy if-then rules. The concept and method presented in this paper are illustrated through one traditional academic pattern recognition problem and one highly nonlinear system identification problem.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
L.A. Zadeh,” Fuzzy Sets,” Information and Control, vol. 8, pp.338–353, 1965.
M. C. Su, A Neural Network Approach to Knowledge Acquisition, Ph.D. thesis, University of Maryland, August, 1993.
H. Takagi and I. Hayashi, ”NN-driven fuzzy reasoning”, Int. J. Approximate Reasoning, vol.5, No3, PP. 191–212, May, 1991.
L. X. Wang, Adaptive Fuzzy Systems and Control: Design and Stability Analysis, Prentice Hall, Inc. New Jersey, 1994.
C. T. Lin C. S. G. Lee, Neural network-based fuzzy logic control and decision system, ”IEEE Trans. Computers, vol.40, No.12, PP.1320–1336, 1991.
B. Kosko, Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence, Prentice-Hall, NJ, 1992.
P. K. Simpson, ”Fuzzy min-max neural networks-part 1: Classification,” IEEE Trans. on Neural Networks, vol. 3, pp. 776–786, Sep. 1992.
N. DeClaris and M. C. Su, ”A novel class of neural networks with quadratic junctions, ”IEEE Int. Conf. on systems, Man, and Cybernetics, PP. 1557–1562, 1991 (Received the 1992 Franklin V. Taylor Award).
N. DeClaris and M. C. Su, ”Introduction to the theory and application of neural networks with quadratic junctions, ”IEEE Int. Conf. on systems, Man, and Cybernetics, PP. 1320–1325, 1992.
T. Poggio and F. Girosi, ”Networks for approximation and learning,” Proc. of the IEEE, vol.78, No.9, PP.1481–1497, 1990.
K. J. Cios and N. Liu, ”A machine learning method for generation of a neural architecture: a continuous ID3 algorithm,” IEEE Trans. on Neural Networks, vol. 3, pp. 280–291, March 1992.
K. Lang and M. J. Witbrock, ”Learning to tell two spirals apart,” Proc. Connectionist Models summer school, pp. 52–59, 1988.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
DeClaris, N., Su, MC. (1995). A self-learning neuro-fuzzy system. In: Antsaklis, P., Kohn, W., Nerode, A., Sastry, S. (eds) Hybrid Systems II. HS 1994. Lecture Notes in Computer Science, vol 999. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60472-3_6
Download citation
DOI: https://doi.org/10.1007/3-540-60472-3_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60472-3
Online ISBN: 978-3-540-47519-4
eBook Packages: Springer Book Archive