A NEW ADAPTIVE POLYNOMIAL NEURAL-NETWORK

This paper considers the problem of the construction of nonlinear mapp ing by using an adaptive polynomial neural network [1], implementing a learning rule. First we apply the method to a two-class pattern recog nition problem. We use one high order neuron with a threshold element ranging from -1 to +1. Positive output means class 1 and negative outp ut means class 2. The main idea of the method proposed is that the wei ghts are adjusted automatically in such a way to move the decision bou ndary to a place of low pattern density. Once reached the convergence, to improve the generalization ability, we add a growing noise to the data available. The training is performed by a steepest-descent algori thm on the weights.