论文信息 - A LEARNING METHOD OF FUZZY REASONING BY GENETIC ALGORITHMS

A LEARNING METHOD OF FUZZY REASONING BY GENETIC ALGORITHMS

Fuzzy Rule Base Systems (FRBS) has been shown to be an important tool for problems where, due to the complexity or the imprecision, classical tools are unsuccessful. In [3,14] it has been proved that FRBS are universal approximators in the sense that for any continuous system it is possible to find a set of fuzzy rules able of approximating it with arbitrary accuracy. Now, the question is: How can we find this set of rules?.

[1] Rudolf Kruse,et al. Symbolic and Quantitative Approaches to Uncertainty , 1991, Lecture Notes in Computer Science.

[2] Chyck Karr,et al. Applying genetics to fuzzy logic , 1991 .

[3] L. Wang,et al. Fuzzy systems are universal approximators , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[4] K. Dejong,et al. An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[5] Juan Luis Castro,et al. Fuzzy logic controllers are universal approximators , 1995, IEEE Trans. Syst. Man Cybern..

[6] Charles L. Karr,et al. Genetic algorithms for fuzzy controllers , 1991 .

[7] Elisabetta Binaghi,et al. Learning of Uncertain Classification Rules in Medical Diagnosis , 1991, ECSQARU.

[8] David E. Goldberg,et al. Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9] Pei-Zhuang Wang,et al. On Generating Linguistic Rules for Fuzzy Models , 1988, IPMU.

[10] John H. Holland,et al. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[11] Chuen-Chien Lee,et al. A self‐learning rule‐based controller employing approximate reasoning and neural net concepts , 1991, Int. J. Intell. Syst..