Simplifying the Supervised Learning of Kerr Nonlinearity Compensation Algorithms by Data Augmentation

Abstract

We propose a data augmentation technique to improve performance and decrease complexity of the supervised learning of nonlinearity compensation algorithms. We demonstrate both numerically and experimentally that the augmentation allows reducing the training dataset size up to 6 times while keeping the same post-compensation bit-error rate.

Publication DOI: https://doi.org/10.1109/ECOC48923.2020.9333417
Divisions: College of Engineering & Physical Sciences > Aston Institute of Photonics Technology (AIPT)
College of Engineering & Physical Sciences > School of Informatics and Digital Engineering > Electrical and Electronic Engineering
College of Engineering & Physical Sciences
Additional Information: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Event Title: 2020 European Conference on Optical Communications
Event Type: Other
Event Dates: 2020-12-06 - 2020-12-10
Uncontrolled Keywords: Computer Networks and Communications,Electronic, Optical and Magnetic Materials,Instrumentation,Atomic and Molecular Physics, and Optics
ISBN: 978-1-7281-7362-7, 978-1-7281-7361-0
Full Text Link:
Related URLs: https://ieeexpl ... ocument/9333417 (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Conference contribution
Published Date: 2021-02-04
Accepted Date: 2020-12-01
Authors: Neskorniuk, Vladislav
Freire de Carvalho Souza, Pedro Jorge (ORCID Profile 0000-0003-3145-1018)
Napoli, Antonio
Spinnler, Bernhard
Schairer, Wolfgang
Prilepsky, Jaroslaw E. (ORCID Profile 0000-0002-3035-4112)
Costa, Nelson
Turitsyn, Sergei K. (ORCID Profile 0000-0003-0101-3834)

Download

[img]

Version: Draft Version

| Preview

Export / Share Citation


Statistics

Additional statistics for this record