Efficient Training of Volterra Series-Based Pre-distortion Filter Using Neural Networks
arXiv:2112.06637
Abstract
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.
Accepted for presentation in OFC 2022