Role of chaos in swarm intelligence - A preliminary analysis

Abstract

This paper investigates the relation between chaos and swarm intelligence. The swarm intelligent model is represented as an iterated function system (IFS). The dynamic trajectory of the particle is sensitive on the parameter values of IFS. The Lyapunov exponent and the correlation dimension were calculated and analyzed. Our preliminary research results illustrate that the performance of the swarm intelligent model depends on the sign of the maximum Lyapunov exponent. The particle swarm with a high maximum Lyapunov exponent usually achieved better performance, especially for multi-modal functions.