论文信息 - FUZZY NEURAL NETWORKS ARE UNIVERSAL APPROXIMATORS

FUZZY NEURAL NETWORKS ARE UNIVERSAL APPROXIMATORS

In this paper we examine the capacity of fuzzy neural networks. These networks are multilayer feedforword nets whose processing elements { the formal neurons { operate on fuzzy numbers instead of real numbers. We show that these fuzzy neural networks can approximate fuzzy continuous real functions on a compact domain to any degree of accuracy.

T H Feuring | W M Lippe | T. Feuring | W. Lippe

[1] Thomas Feuring. Fuzzy-Neuronale Netze: von kooperativen über hybride zu fusionierten vage-konnektionistischen Systemen , 1995 .

[2] Madan M. Gupta,et al. On the principles of fuzzy neural networks , 1994 .

[3] Ken-ichi Funahashi,et al. On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[4] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[5] James J. Buckley,et al. Can fuzzy neural nets approximate continuous fuzzy functions , 1994 .