End-to-End Optimized Nonlinear Fourier Transform-Based Coherent Communications

We propose a jointly optimized nonlinear Fourier transform (NFT)-based transmitter and neural network-based receiver. More than two orders of magnitude improvement in bit error ratio is numerically reported for 5600-km transmission compared to a standard NFT system.

Saved in:
Bibliographic Details
Published in2020 Conference on Lasers and Electro-Optics (CLEO) pp. 1 - 2
Main Authors Gaiarin, Simone, Jones, Rasmus T., Ros, Francesco Da, Zibar, Darko
Format Conference Proceeding
LanguageEnglish
Published OSA 01.05.2020
Subjects
Artificial neural networks
Fourier transforms
Optical transmitters
Optimization
Receivers
Online AccessGet full text

Cover

More Information
Summary:We propose a jointly optimized nonlinear Fourier transform (NFT)-based transmitter and neural network-based receiver. More than two orders of magnitude improvement in bit error ratio is numerically reported for 5600-km transmission compared to a standard NFT system.