Nonlinear channel equalization using multilayer perceptrons with information-theoretic criterion

The minimum error entropy criterion was recently suggested in adaptive system training as an alternative to the mean-square-error criterion, and it was shown to produce better results in many tasks. The authors apply a multilayer perceptron scheme trained with this information theoretic criterion to the problem of nonlinear channel equalization. In our simulations, we use a realistic nonlinear channel model, which is encountered when practical power amplifiers are used in the transmitter. The bandwidth-efficient 16-QAM scheme, which uses a dispersed constellation, is assumed