Neural Computation, cilt.8, sa.5, ss.939-949, 1996 (Scopus)
The problems arising from the use of nonlinear multipliers in multilayer neural network synapse structures are discussed. The errors arising from the neglect of nonlinearitiès are shown and the effect of training in eliminating these errors is discussed. A method for predicting the final errors resulting from nonlinearities is described. Our approximate results are compared with the results from circuit simulations of an actual multiplier circuit.