Model-Based Deep Learning of Joint Probabilistic and Geometric Shaping for Optical Communication

Vladislav Neskorniuk, Andrea Carnio, Domenico Marsella, Sergei K. Turitsyn, Jaroslaw E. Prilepsky, Vahid Aref

Research output: Chapter in Book/Published conference outputConference publication

Abstract

Autoencoder-based deep learning is applied to jointly optimize geometric and probabilistic constellation shaping for optical coherent communication. The optimized constellation shaping outperforms the 256 QAM Maxwell-Boltzmann probabilistic distribution with extra 0.05 bits/4D-symbol mutual information for 64 GBd transmission over 170 km SMF link.

Original languageEnglish
Title of host publication2022 Conference on Lasers and Electro-Optics, CLEO 2022 - Proceedings
PublisherIEEE
Number of pages2
ISBN (Electronic)9781957171050
Publication statusPublished - 23 Sep 2022
Event2022 Conference on Lasers and Electro-Optics, CLEO 2022 - San Jose, United States
Duration: 15 May 202220 May 2022
https://www.cleoconference.org/home/schedule/

Publication series

NameConference on Lasers and Electro-Optics, CLEO

Conference

Conference2022 Conference on Lasers and Electro-Optics, CLEO 2022
Country/TerritoryUnited States
CitySan Jose
Period15/05/2220/05/22
Internet address

Bibliographical note

Funding Information:
Acknowledgements: This project has received funding from EU Horizon 2020 program under the Marie Skłodowska-Curie grant agreement No. 766115 (FONTE). SKT acknowledges the support of EPSRC project TRANSNET.

Fingerprint

Dive into the research topics of 'Model-Based Deep Learning of Joint Probabilistic and Geometric Shaping for Optical Communication'. Together they form a unique fingerprint.

Cite this