On the alleviation of the problem of local minima in back-propagation
Proceedings of second world congress on Nonlinear analysts
Computing Nash equilibria through computational intelligence methods
Journal of Computational and Applied Mathematics - Special issue: Selected papers of the international conference on computational methods in sciences and engineering (ICCMSE-2003)
Analyzing cooperative coevolution with evolutionary game theory
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
International Journal of Swarm Intelligence Research
Hi-index | 7.29 |
Particle swarm optimization (PSO) is an evolutionary algorithm used extensively. This paper presented a new particle swarm optimizer based on evolutionary game (EGPSO). We map particles' finding optimal solution in PSO algorithm to players' pursuing maximum utility by choosing strategies in evolutionary games, using replicator dynamics to model the behavior of particles. And in order to overcome premature convergence a multi-start technique was introduced. Experimental results show that EGPSO can overcome premature convergence and has great performance of convergence property over traditional PSO.