Title :
General fuzzy systems are function approximators
Author_Institution :
Dept. of Physiol. & Biophys., Texas Univ. Med. Branch, Galveston, TX, USA
Abstract :
Proves, in a constructive way, that general fuzzy systems can uniformly approximate any real continuous function on a compact domain to any degree of accuracy. Furthermore, the author reveals the underlying mechanism of such function approximation: the fuzzy systems can uniformly approximate any polynomials which, according to the Weierstrass approximation theorem, can uniformly approximate any continuous function on a compact domain. It is shown that as the approximation accuracy approaches zero, the number of fuzzy rules needed for the approximation approaches ∞
Keywords :
approximation theory; function approximation; fuzzy logic; fuzzy set theory; polynomials; Weierstrass approximation theorem; approximation accuracy; compact domain; continuous function; function approximators; fuzzy rules; general fuzzy systems; polynomials; real continuous function; Biomedical computing; Biomedical engineering; Biophysics; Control systems; Function approximation; Fuzzy control; Fuzzy sets; Fuzzy systems; Hybrid intelligent systems; Physiology;
Conference_Titel :
Decision and Control, 1993., Proceedings of the 32nd IEEE Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-1298-8
DOI :
10.1109/CDC.1993.325486