The method of operating a neural network recited in claim 17 wherein said polynomial expansion has the form: ##EQU5## wherein y represents the output of the neural network; wherein wi-1 represents the weight value for the ith neuron;wherein xi, xj, xk represent inputs to said neural network; wherein n is a positive integer; and wherein f1(i) through f6(i,j,k) are index-generating functions. 22.