Title :
On the mapping capabilities of fuzzy inference systems
Author_Institution :
Dept. of Control Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
It is demonstrated that fuzzy inference systems can be used effectively for function approximation. A class of fuzzy inference systems under consideration has the characteristic that the output fuzzy set of every fuzzy logical rule is a singleton. It is shown that the class of fuzzy inference systems suggested is capable of approximating any real continuous function to any desired degree of accuracy, provided sufficient fuzzy logical rules are available. To investigate a direct application of results, the relationships between these fuzzy inference systems and multilayer neural networks are discussed
Keywords :
function approximation; fuzzy logic; fuzzy set theory; inference mechanisms; neural nets; function approximation; fuzzy inference systems; fuzzy logical rule; fuzzy set theory; mapping capabilities; multilayer neural networks; singleton; Control engineering; Control systems; Function approximation; Fuzzy control; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Multi-layer neural network; Neural networks;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.226904
