Research on Optimization Learning of Radial Basis Function Recursive Least Square Algorithm

In this paper,Due to slow restrain rate and lower precision accuracy in the BP neural network of three layers perception machine,A cooperative adaptive algorithm based on the Radial Basis Function(RBF)recursive least square algorithm and adaptive learning for optimizing shape parameter of RBF is proposed,by which training of RBF neural network and simulation experiments are done.The results show that the algorithm described in this paper have more fast restrain rate of network than BP algorithm and RBF algorithm of fixed αvalue.in the end,We apply trained neural network to estimate mine gas gushing,and precision accuracy is enhanced rapidly.So the algorithm proposed in this paper has high of application value.