Title :
The study of fuzzy functions. I. Universal approximators
Author :
Buckley, James J. ; Feuring, Thomas
Author_Institution :
Alabama Univ., Birmingham, AL, USA
Abstract :
We show how to construct a large class of universal approximators for fuzzy functions (which continuously map fuzzy numbers into fuzzy numbers and are the extension principle extensions of continuous real-valued functions). One important application is that layered, feedforward, neural nets, with real weights and bias terms and fuzzy signals, whose output is computed using the extension principle, are universal approximators for these functions
Keywords :
approximation theory; feedforward neural nets; fuzzy neural nets; multilayer perceptrons; bias terms; continuous real-valued function extensions; fuzzy functions; fuzzy number mapping; fuzzy signals; layered feedforward neural nets; multilayer feedforward neural nets; real weights; universal approximators; Differential equations; Feedforward neural networks; Fuzzy neural networks; Fuzzy sets; Neural networks; Neurons;
Conference_Titel :
Fuzzy Systems Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4863-X
DOI :
10.1109/FUZZY.1998.687582
