Utilization of neural network signal processing in the design of a predistorter for a nonlinear telecommunication channel

In this paper, we describe the use of neural networks to implement a predistorter for a nonlinear digital telecommunication channel. Since most of the signals used in digital communication are complex, the usual neural network signal processing techniques used in system identification (which typically assume real signals) can not be utilized. Therefore, we use a complex neural network which was formerly utilized by Benvenuto et al. (1992) to design an equalizer for a nonlinear channel.<>