Learning algorithm and hidden node selection scheme for local coupled feedforward neural network classifier

In this paper, a neural classifier based on the newly developed local coupled feedforward neural network, which may improve the convergence of BP learning significantly, is developed. A binary threshold unit is used as the output node of the classifier. A general error gradient of the output node is defined for the BP training of the classifier. And a hidden node selection scheme is developed for the local coupled feedforward neural network. In addition, we derive a result on the “universal approximation” property of the local coupled feedforward neural network with an arbitrary group of window functions, which can cover the region of training samples. Simulation results show that the general error gradient and the hidden node selection scheme work well.