Combining nonlinear Fourier transform and neural network-based processing in optical communications

Abstract

We propose a method to improve the performance of the nonlinear Fourier transform (NFT)-based optical transmission system by applying the neural network post-processing of the nonlinear spectrum at the receiver. We demonstrate through numerical modeling about one order of magnitude bit error rate improvement and compare this method with machine learning processing based on the classification of the received symbols. The proposed approach also offers a way to improve numerical accuracy of the inverse NFT; therefore, it can find a range of applications beyond optical communications.

Publication DOI: https://doi.org/10.1364/OL.394115
Divisions: Engineering & Applied Sciences > Aston Institute of Photonics Technology
Engineering & Applied Sciences
Engineering & Applied Sciences > Electrical, Electronic & Power Engineering
Additional Information: Published by The Optical Society under the terms of the Creative Commons Attribution 4.0 License. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI. Funding: H2020 Marie Skłodowska-Curie Actions (GA2015-713694, 751561); Engineering and Physical Sciences Research Council (Project TRANSNET EP/R035342/1); Leverhulme Trust (Grant RP-2018-063).
Uncontrolled Keywords: Atomic and Molecular Physics, and Optics
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
https://www.osa ... i=ol-45-13-3462 (Publisher URL)
PURE Output Type: Article
Published Date: 2020-07-01
Published Online Date: 2020-06-22
Accepted Date: 2020-05-15
Authors: Kotlyar, Oleksandr ( 0000-0002-2744-0132)
Pankratova, Maryna
Kamalian-Kopae, Morteza ( 0000-0002-6278-976X)
Vasylchenkova, Anastasiia ( 0000-0002-6997-9427)
Prilepsky, Jaroslaw E. ( 0000-0002-3035-4112)
Turitsyn, Sergei K. ( 0000-0003-0101-3834)

Download

[img]

Version: Published Version

License: Creative Commons Attribution

| Preview

Export / Share Citation


Statistics

Additional statistics for this record