DocumentCode
2274416
Title
Hybrid fuzzy neural nets are universal approximators
Author
Buckley, James J. ; Hayashi, Yoichi
Author_Institution
Dept. of Math., Alabama Univ., Birmingham, AL, USA
fYear
1994
fDate
26-29 Jun 1994
Firstpage
238
Abstract
It is known that regular fuzzy neural nets, based on standard fuzzy arithmetic and the extension principle, can not be universal approximators. This negative result is surprising since (regular) neural nets are universal approximators. We argue that hybrid fuzzy neural nets, not necessarily based only on standard fuzzy arithmetic, can be universal approximators
Keywords
approximation theory; fuzzy neural nets; fuzzy set theory; transfer functions; fuzzy arithmetic; hybrid fuzzy neural nets; transfer function; universal approximators; Control systems; Digital arithmetic; Extraterrestrial measurements; Fuzzy control; Fuzzy neural networks; Fuzzy systems; Hybrid intelligent systems; Mathematics; Neural networks; Neurons;
fLanguage
English
Publisher
ieee
Conference_Titel
Fuzzy Systems, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the Third IEEE Conference on
Conference_Location
Orlando, FL
Print_ISBN
0-7803-1896-X
Type
conf
DOI
10.1109/FUZZY.1994.343759
Filename
343759
Link To Document