Cooperative learning in neural networks using particle swarm optimizers

Abstract

This paper presents a method to employ particle swarms optimizers in a cooperative configuration. This is achieved by splitting the input vector into several sub-vectors, each which is optimized cooperatively in its own swarm. The application of this technique to neural network training is investigated, with promising results. Keywords: Particle swarms, cooperative learning, optimization Computing Review Categories: G.1.6, I.2.6 1 Introduction Particle Swarm Optimizers (PSOs) have previously been used to train neural networks[6, 10] and generally met with success. The advantage of the PSO over many of the other optimization algorithms is its relative simplicity. This paper aims to improve the performance of the basic PSO by partitioning the input vector into several subvectors. Each sub-vector is then allocated its own swarm. In Section 2, a brief overview of PSOs is presented, followed by a discussion of how cooperative behavior can be implemented through a splitting technique i...