Dynamic node creation and fast learning algorithm for a hybrid feedforward neural network

Presents an algorithm of dynamic node creation and weights learning for a hybrid feedforward neural network (HFNN) which consists of a linear model and a multilayer neural network. The algorithm is only based on linear least squares, and no iterative learning process is needed. According to the demand of model precision, the algorithm determines the best weights of network and the minimal number of hidden nodes automatically. Compared with the well-known backpropagation network, simulation results show that the new learning algorithm for the HFNN is efficient in model precision, rate of convergence and generalization ability.