English

Fully-blind Neural Network Based Equalization for Severe Nonlinear Distortions in 112 Gbit/s Passive Optical Networks

Signal Processing 2024-01-19 v1 Machine Learning

Abstract

We demonstrate and evaluate a fully-blind digital signal processing (DSP) chain for 100G passive optical networks (PONs), and analyze different equalizer topologies based on neural networks with low hardware complexity.

Keywords

Cite

@article{arxiv.2401.09579,
  title  = {Fully-blind Neural Network Based Equalization for Severe Nonlinear Distortions in 112 Gbit/s Passive Optical Networks},
  author = {Vincent Lauinger and Patrick Matalla and Jonas Ney and Norbert Wehn and Sebastian Randel and Laurent Schmalen},
  journal= {arXiv preprint arXiv:2401.09579},
  year   = {2024}
}

Comments

Accepted and to be presented at the Optical Fiber Communication Conference (OFC) 2024