基于RBF神经网络的非线性回归模型

RBF neural network namely radial basis function neural network is a kind of efficient feedforward neural network, it has the best approximation performance and global optimal characteristics than other prior to network ,it simple structure and training speed. Meanwhile, it is also a kind of can be widely used in pattern recognition, nonlinear function approximation and other areas of neural network model. This paper using the nonlinear regression characteristic of radial basis RBF neural network to simulation the known function . The design model has a reliable good performance to compared to the antiderivative output results between the result after radial basis RBF neural network nonlinear regression model simulation.