Title :
Are regular fuzzy neural nets universal approximators?
Author :
Buckley, James J. ; Hayashi, Yoichi
Author_Institution :
Dept. of Math., Alabama Univ., Birmingham, AL, USA
Abstract :
We argue that if fuzzy neural nets use fuzzy arithmetic based on the extension principle they cannot be universal approximators. This negative result is important when contrasted with the fact that neural nets are universal approximators.
Keywords :
approximation theory; feedforward neural nets; fuzzy neural nets; fuzzy set theory; fuzzy arithmetic; fuzzy neural nets; fuzzy set theory; universal approximators; Control systems; Extraterrestrial measurements; Fuzzy control; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Hybrid intelligent systems; Mathematics; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714015
