Learning Fuzzy Set Neural Networks by Genetic Algorithms

Abstract

An important class of current fuzzy neural networks, called fuzzy set neural networks (FSNNs), is one in which all the inputs, synaptic weights, and outputs may be vectors of fuzzy sets. One of the most difficult tasks in the development of these FSNNs is the lack of efficient learning algorithms. In this article we employ genetic algorithms (GAs) techniques to design a FSNN. We first study the parameterization of the synaptic weights to be learned in an FSNN, and then the evolutionary learning procedure is discussed in each genetic cycle. Some simulation results on the application of a FSNN to the problem of backing a truck are presented. Finally, the self-organizing space during reproduction of genes in GAs is studied.