Chaos optimization algorithm design for fuzzy neural network
模糊神经网络的混沌优化算法设计

An optimization algorithmdesign based on chaotic variable is proposed for multilayer fuzzy neural network.Off-line optimization uses chaos algorithmand chaos variables are applied to searchfor networkstructure and parameters ,in which thenetworkis in dynamic chaos state .An approximate optimal network structure and parameters are found from dynamic networkaccordingto performance index.On-line optimization uses gradient descent algorithmand the initial values of gradient descentsearching are parameters approximately global optimal values fromchaos searching,the parameters of fuzzy neural network are fur-ther adjusted.The global optimal values of networkare searched quickly by means of combination of chaos global searchingand gra-dient descent local searching.Finally,second order delaysystemis simulated,andthe results showthat the chaos optimal control is ofhigh precision,small overshoot ,fast response and good robustness .