Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Neural Network Assisted Geometric Shaping for 800Gbit/s and 1Tbit/s Optical Transmission

Not Accessible

Your library or personal account may give you access

Abstract

End-to-end learning for amplified and unamplified links including binary mapping is proposed to improve the performance of optical coherent systems. 1.0dB and 1.2dB gains are demonstrated on coherent 92GbaudDP-32QAM 800Gb/s and 82GbaudDP- 128QAM 1Tb/s measurements, respectively.

© 2020 The Author(s)

PDF Article
More Like This
Neural Network-Based Soft-Demapping for Nonlinear Channels

Maximilian Schaedler, Stefano Calabrò, Fabio Pittalà, Christian Bluemm, Maxim Kuschnerov, and Stephan Pachnicke
W3D.2 Optical Fiber Communication Conference (OFC) 2020

Single-carrier 800 Gbit/s and 1.2 Tbit/s Transmission Using 96 GBaud Commercial Optoelectronic Components

ZHENG Qiang, YANG Hong, WANG Longbao, XIAO Zhuopeng, and ZHANG Huijian
T1B.4 Asia Communications and Photonics Conference (ACP) 2021

800 Gbit/s Dual Channel Transmitter with 1.056 Tbit/s Gross Rate

Karsten Schuh, Fred Buchali, Wilfried Idler, Tobias A. Eriksson, Wolfgang Templ, Lars Altenhain, Ulrich Dümler, Rolf Schmid, and Michael Möller
Tu2E.6 Optical Fiber Communication Conference (OFC) 2017

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All Rights Reserved