Minimization of multivalued multithreshold perceptrons using genetic algorithms

Abstract

We address the problem of computing and learning multivalued multithreshold perceptrons. Every n-input X-valued logic function can be implemented using a (k, s)-perceptron, for some number of thresholds s. We propose a genetic algorithm to search for an optimal (k, s)-perceptron that efficiently realizes a given multiple-valued logic function, that is to minimize the number of thresholds. Experimental results show that the genetic algorithm find optimal solutions in most cases.