Paper ID: 2112.06637

Efficient Training of Volterra Series-Based Pre-distortion Filter Using Neural Networks

Vinod Bajaj, Mathieu Chagnon, Sander Wahls, Vahid Aref

We present a simple, efficient "direct learning" approach to train Volterra series-based digital pre-distortion filters using neural networks. We show its superior performance over conventional training methods using a 64-QAM 64-GBaud simulated transmitter with varying transmitter nonlinearity and noisy conditions.

Submitted: Dec 13, 2021