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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Plabst, Daniel, Prinz, Tobias, Diedolo, Francesca, Wiegart, Thomas, Böcherer, Georg, Hanik, Norbert, Kramer, Gerhard
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910580910063616
author Plabst, Daniel
Prinz, Tobias
Diedolo, Francesca
Wiegart, Thomas
Böcherer, Georg
Hanik, Norbert
Kramer, Gerhard
author_facet Plabst, Daniel
Prinz, Tobias
Diedolo, Francesca
Wiegart, Thomas
Böcherer, Georg
Hanik, Norbert
Kramer, Gerhard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15767
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity
Plabst, Daniel
Prinz, Tobias
Diedolo, Francesca
Wiegart, Thomas
Böcherer, Georg
Hanik, Norbert
Kramer, Gerhard
Information Theory
Signal Processing
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.
title Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity
topic Information Theory
Signal Processing
url https://arxiv.org/abs/2408.15767