基于混合粒子群算法的RBF神经网络参数优化

Strategic Study of RBF Neural Network Parameter Optimization

针对径向基函数(RBF)神经网络中心参数的优化问题,提出了一种混合粒子群优化算法。该算法应用灰色关联理论定义了粒子群的灰色相似度,分两个阶段对标准的粒子群优化算法(PSO)的全局和局部搜索能力做了改进和提高。在仿真实验中,应用该方法对典型的Mackey-Glass混沌时间序列进行了预测,并与标准的K均值算法、遗传算法和粒子群算法进行了比较,其结果表明,所预测的各项误差均低于其他常规算法的预测结果。

A hybrid particle swarm optimization algorithm is proposed and applied to optimize the parameters of radial basis function network. According to grey interrelation theory, the grey similarity of particles is defined, and the global and local searching ability of the particle swarm is improved in two phases. The optimized network predicts the typical Mackey-Glass chaos sequence. When comprised to the K cluster algorithm, genetic algorithm and particle swami algorithm, simulation results show that the arrived errors are far smaller than the corresponding part of other algorithms above.