Interference Cancellation for Pam Modulation Using Neural Networks

Recently, novel equalizer structures combining traditional transversal equalizers and neural networks have been introduced for adaptive discrete-signal detection. It has been shown that the equalizer performance can be improved using neural networks, especially in compensating nonlinear distortions. In addition to noise and nonlinear distortions various interfering signals may be present. In this paper, the behavior of the neural equalizers in the presence of random interference has been investigated. New adaptive structures for compensating interference will be presented.