Title

Universal Approximation with Uninorm-Based Fuzzy Neural Networks

Authors

Andre Lemos, Federal University of Minas Gerais
Vladik Kreinovich, University of Texas at El PasoFollow
Walmir Caminhas, Federal University of Minas Gerais
Fernando Gomide, University of Campinas

Publication Date

12-2010

Comments

Technical Report: UTEP-CS-10-59

Published in Proceedings of the 30th Annual Conference of the North American Fuzzy Information Processing Society NAFIPS'2011, El Paso, Texas, March 18-20.

Abstract

Fuzzy neural networks are hybrid models capable to approximate functions with high precision and to generate transparent models, enabling the extraction of valuable information from the resulting topology. In this paper we will show that the recently proposed fuzzy neural network based on weighted uninorms aggregations uniformly approximates any real functions on any compact set. We will describe the network topology and inference mechanism and show that the universal approximation property of this network is valid for a given choice of operators.