Title :
Can neural nets be universal approximators for fuzzy functions?
Author :
Buckley, J.J. ; Hayashi, Yoichi
Author_Institution :
Dept. of Math., Alabama Univ., Birmingham, AL, USA
Abstract :
We first argue that the extension principle is too computationally involved to be an efficient way for a computer to evaluate fuzzy functions. We then suggest using α-cuts and interval arithmetic to compute the values of fuzzy functions. Using this method of computing fuzzy functions, we then show that neural nets are universal approximators for (computable) fuzzy functions, when we only input non-negative, or non-positive, fuzzy numbers
Keywords :
feedforward neural nets; function approximation; fuzzy set theory; multilayer perceptrons; α-cuts; extension principle; fuzzy functions; interval arithmetic; neural nets; nonnegative fuzzy numbers; nonpositive fuzzy numbers; universal approximators; Arithmetic; Computer science; Feedforward neural networks; Fuzzy neural networks; Fuzzy sets; Mathematics; Neural networks;
Conference_Titel :
Fuzzy Systems, 1997., Proceedings of the Sixth IEEE International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7803-3796-4
DOI :
10.1109/FUZZY.1997.622863
