Skip to Main content Skip to Navigation
Journal articles

Attention-Based Neural Network Equalization in Fiber-Optic Communications

Abtin Shahkarami 1, 2 Mansoor Yousefi 1, 2 Yves Jaouën 1, 2 
2 GTO - Télécommunications Optiques
LTCI - Laboratoire Traitement et Communication de l'Information
Abstract : An attention mechanism is integrated into neural network-based equalizers to prune the fully-connected output layer. For a 100 GBd 16-QAM 20 × 100 km SMF transmission, this approach reduces the computational complexity by ∼15% in a CNN+LSTM model.
Complete list of metadata

https://hal.telecom-paris.fr/hal-03585118
Contributor : Abtin Shahkarami Connect in order to contact the contributor
Submitted on : Tuesday, February 22, 2022 - 10:53:20 PM
Last modification on : Saturday, April 9, 2022 - 11:10:01 AM
Long-term archiving on: : Monday, May 23, 2022 - 7:58:16 PM

File

APC2021__open_access_version_....
Files produced by the author(s)

Identifiers

Collections

Citation

Abtin Shahkarami, Mansoor Yousefi, Yves Jaouën. Attention-Based Neural Network Equalization in Fiber-Optic Communications. Asia Communications and Photonics Conference 2021, 2021, ⟨10.1364/acpc.2021.m5h.3⟩. ⟨hal-03585118⟩

Share

Metrics

Record views

70

Files downloads

41