粒子群优化算法训练模糊神经网络

Training Fuzzy Neural Networks Using Particle Swarm Optimizer

研究合适的神经网络学习算法是令人感兴趣的问题。提出一种用粒子群优化(PSO)算法训练模糊神经网络的方法。PSO的位置向量对应模糊神经网络的权值向量,而PSO的适应函数对应模糊神经网络的目标函数,然后,通过演化PSO达到训练模糊神经网络的目的。用PSO算法训练模糊神经网络预测混沌时间序列的实验结果表明PSO算法性能优良,适合训练模糊神经网络。

Training artificial neural networks is one of the interesting research fields in artificial neural networks society. In order to improve performances of fuzzy neural networks (FNN), a method of training FNN using particle swarm optimizers (PSO) is proposed. Position vector of a PSO is wight vector of trained FNN, and fitness function of the PSO is object function of trained FNN, the FNN is then trained by evolving the PSO. The experimental results that train fuzzy neural networks with PSO for predicting chaotic time series are good.