Unscented Kalman Filter-Trained Recurrent Neural Equalizer for Time-Varying Channels

Recurrent neural networks have been successfully applied to communications channel equalization because of their capability of modelling nonlinear dynamic systems. The major problems of gradient descent learning techniques, commonly employed to train recurrent neural networks, are slow convergence rates and long training sequences. This paper presents a decision feedback equalizer using a recurrent neural network trained with the unscented Kalman filter (UKF). The main features of the proposed recurrent neural equalizer are fast convergence and good performance using relatively short training symbols. Experimental results for time-varying channels are presented to evaluate the performance of the proposed approaches over a conventional recurrent neural equalizer.