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

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

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 informat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-04
Hauptverfasser: Neskorniuk, Vladislav, Carnio, Andrea, Marsella, Domenico, Turitsyn, Sergei K, Prilepsky, Jaroslaw E, Aref, Vahid
Format: Artikel
Sprache:eng
Schlagworte:
Deep learning
Optical communication
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:2331-8422