Functional equivalence between neural networks and fuzzy systems with sinusoidal membership functions

Author

Jin, Liang ; Gupta, Madan M.

Author_Institution

Intelligent Syst. Res. Lab., Saskatchewan Univ., Saskatoon, Sask., Canada

fYear

1995

Firstpage

305

Lastpage

310

Abstract

The functional equivalence between multilayered neural networks (MNNs) and fuzzy systems with a singleton fuzzifier, a product inference, a centroid defuzzifier and a sinusoidal membership function is discussed in this paper. First, a normalized structure of MNNs is given in terms of input-output equations of MNNs. Fuzzy basis function network (FBFN) expansions of multi-input single-output (MISO) fuzzy systems are then given in order to describe the input-output relationships of fuzzy systems. Sinusoidal membership functions are introduced for fuzzy systems with a graded value over [0,1]. Functional equivalence between the two systems is analytically shown. Finally, the universal approximation capability of FBFNs is briefly discussed

Keywords

feedforward neural nets; fuzzy neural nets; fuzzy systems; multilayer perceptrons; centroid defuzzifier; functional equivalence; fuzzy basis function networks; graded value; input-output equations; multi-input single-output fuzzy systems; multilayered neural networks; normalized structure; product inference; singleton fuzzifier; sinusoidal membership function; universal approximation capability; Artificial neural networks; Educational institutions; Equations; Fuzzy systems; Intelligent networks; Intelligent systems; Laboratories; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Uncertainty Modeling and Analysis, 1995, and Annual Conference of the North American Fuzzy Information Processing Society. Proceedings of ISUMA - NAFIPS '95., Third International Symposium on

Conference_Location

College Park, MD

Print_ISBN

0-8186-7126-2

Type

conf

DOI

10.1109/ISUMA.1995.527712

Filename

527712