Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity

Daniel Plabst; Tobias Prinz; Francesca Diedolo; Thomas Wiegart; Georg Böcherer; Norbert Hanik; Gerhard Kramer

Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity

Information Theory 2024-08-29 v1 Signal Processing math.IT

Authors: Daniel Plabst , Tobias Prinz , Francesca Diedolo , Thomas Wiegart , Georg Böcherer , Norbert Hanik , Gerhard Kramer

View on arXiv ↗ PDF ↗

Abstract

Neural networks (NNs) inspired by the forward-backward algorithm (FBA) are used as equalizers for bandlimited channels with a memoryless nonlinearity. The NN-equalizers are combined with successive interference cancellation (SIC) to approach the information rates of joint detection and decoding (JDD) with considerably less complexity than JDD and other existing equalizers. Simulations for short-haul optical fiber links with square-law detection illustrate the gains.

Keywords

neural network equalizers successive interference cancellation bandlimited channels nonlinearity forward-backward algorithm optical fiber links square-law detection

Cite

@article{arxiv.2408.15767,
  title  = {Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity},
  author = {Daniel Plabst and Tobias Prinz and Francesca Diedolo and Thomas Wiegart and Georg Böcherer and Norbert Hanik and Gerhard Kramer},
  journal= {arXiv preprint arXiv:2408.15767},
  year   = {2024}
}

Comments

Accepted at IEEE Intern. Symp. on Inf. Theory 2024 in Athens. arXiv admin note: substantial text overlap with arXiv:2401.09217

Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity

Abstract

Keywords

Cite

Comments

Related papers