Search

In this paper, we propose an extension of genetic algorithm for neuroevolution of interval-valued neural networks. In the proposed GA, values in the genotypes are not real numbers but intervals. We apply our interval-valued GA (IvGA) to the approximate modeling of interval functions with interval-valued neural networks. Experimental results showed that INNs trained by our IvGA approximated a test function to a certain extent, despite the fact that the learning was not supervised. [ABSTRACT FROM PUBLISHER]

This paper proposes EAs that utilize fuzzy values directly as the genotype values. In the proposed method, each element in a genotype is a fuzzy value. The author extends EA operations for the fuzzy-valued genotypes. Section 2 describes the extensions of EA operations including population initialization, fitness evaluation, and reproduction. The fitness evaluation methods are extended according to application problems, and the reproduction methods are extended according to EA variations. [ABSTRACT FROM PUBLISHER]