Skip to main navigation Skip to search Skip to main content

Attention-Based Neural Network Equalization in Fiber-Optic Communications

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publication2021 Asia Communications and Photonics Conference, ACP 2021 - Proceedings
PublisherOptica Publishing Group (formerly OSA)
ISBN (Electronic)9781957171005
Publication statusPublished - 1 Jan 2021
Event2021 Asia Communications and Photonics Conference, ACP 2021 - Shanghai, China
Duration: 24 Oct 202127 Oct 2021

Publication series

NameAsia Communications and Photonics Conference, ACP
Volume2021-October
ISSN (Print)2162-108X

Conference

Conference2021 Asia Communications and Photonics Conference, ACP 2021
Country/TerritoryChina
CityShanghai
Period24/10/2127/10/21

Fingerprint

Dive into the research topics of 'Attention-Based Neural Network Equalization in Fiber-Optic Communications'. Together they form a unique fingerprint.

Cite this