RECOGNITION OF UNCONSTRAINED HANDWRITTEN NUMERALS BY A RADIAL BASIS FUNCTION NEURAL-NETWORK CLASSIFIER

Among the neural network models the RBF (Radial Basis Function) networ k seems to be quite effective for a pattern recognition task such as h andwritten numeral recognition since it is extremely flexible to accom modate various and minute variations in data. Recently we obtained a g ood recognition rate for handwritten numerals by using an RBF network. In this paper we show how to design an RBF network classifier for a g iven problem in a well defined and easy-to-follow manner. We also repo rt on the experiments to evaluate the performance of the RBF network c lassifier so designed. (C) 1997 Elsevier Science B.V.