关键词: 粒子群优化, 遗传算法, 神经网络

Abstract: Particle swarm optimization algorithm is a kind of stochastic global optimization technology. It finds optimal regions of complex search spaces through the interaction of individuals in a population of particles. This paper proposes a kind uses for training artificial neural network based on GA and the PSO mix algorithm. The algorithm when has next generation, unified crossover and mutation operator and the particle swarm optimization algorithm speed-displacement formula. The algorithm is successfully applied to 3-model and IRIS pattern classification problems, compared with BP, GA and PSO, this algorithm can improve the classification accuracy while speeding up the convergence process , and can avoid premature effective. Simulation results show the effectiveness of the proposed algorithm

Key words: Particle swarm optimization, Genetic algorithm, Neural network