An efficient method to construct a radial basis function neural network classifier and its application to unconstrained handwritten digit recognition

This paper describes a method to construct an RBFN classifier efficiently and effectively. The method determines the middle layer neurons by a fast clustering algorithm, APC-III and computes the optimal weights between the middle and the output layers statistically. The proposed method was applied to an unconstrained handwritten digit recognition. The experiment showed that the method could construct an RBFN classifier fast and the performance of the classifier was as good as the best result previously reported. Our approach presents a good example of the combination of a neural network and a statistical method