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

12/13/2021

∙

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.

READ FULL TEXT

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

Neural Wavetable: a playable wavetable synthesizer using neural networks

Computationally Efficient Neural Image Compression

Multivariate Forecasting of Crude Oil Spot Prices using Neural Networks

Strategic Communication Between Prospect Theoretic Agents over a Gaussian Test Channel

Progressive Transmission using Recurrent Neural Networks

Lightweight and interpretable neural modeling of an audio distortion effect using hyperconditioned differentiable biquads

Using Neural Networks by Modelling Semi-Active Shock Absorber

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

Related Research

Neural Wavetable: a playable wavetable synthesizer using neural networks

Computationally Efficient Neural Image Compression

Multivariate Forecasting of Crude Oil Spot Prices using Neural Networks

Strategic Communication Between Prospect Theoretic Agents over a Gaussian Test Channel

Progressive Transmission using Recurrent Neural Networks

Lightweight and interpretable neural modeling of an audio distortion effect using hyperconditioned differentiable biquads

Using Neural Networks by Modelling Semi-Active Shock Absorber