Standard

Computing continuous nonlinear Fourier spectrum of optical signal with artificial neural networks. / Sedov, Egor; Prylepskiy, Jaroslaw; Chekhovskoy, Igor et al.

Applications of Machine Learning 2021. ed. / Michael E. Zelinski; Tarek M. Taha; Jonathan Howe. SPIE, 2021. 118430J (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11843).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Harvard

Sedov, E, Prylepskiy, J, Chekhovskoy, I & Turitsyn, S 2021, Computing continuous nonlinear Fourier spectrum of optical signal with artificial neural networks. in ME Zelinski, TM Taha & J Howe (eds), Applications of Machine Learning 2021., 118430J, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11843, SPIE, Applications of Machine Learning 2021, San Diego, United States, 01.08.2021. https://doi.org/10.1117/12.2594127

APA

Sedov, E., Prylepskiy, J., Chekhovskoy, I., & Turitsyn, S. (2021). Computing continuous nonlinear Fourier spectrum of optical signal with artificial neural networks. In M. E. Zelinski, T. M. Taha, & J. Howe (Eds.), Applications of Machine Learning 2021 [118430J] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11843). SPIE. https://doi.org/10.1117/12.2594127

Vancouver

Sedov E, Prylepskiy J, Chekhovskoy I, Turitsyn S. Computing continuous nonlinear Fourier spectrum of optical signal with artificial neural networks. In Zelinski ME, Taha TM, Howe J, editors, Applications of Machine Learning 2021. SPIE. 2021. 118430J. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2594127

Author

Sedov, Egor ; Prylepskiy, Jaroslaw ; Chekhovskoy, Igor et al. / Computing continuous nonlinear Fourier spectrum of optical signal with artificial neural networks. Applications of Machine Learning 2021. editor / Michael E. Zelinski ; Tarek M. Taha ; Jonathan Howe. SPIE, 2021. (Proceedings of SPIE - The International Society for Optical Engineering).

BibTeX

@inproceedings{8b97111ab3ba4b388e50dd227a29915e,
title = "Computing continuous nonlinear Fourier spectrum of optical signal with artificial neural networks",
abstract = "In this work, we demonstrate that the high-accuracy computation of the continuous nonlinear spectrum can be performed by using artificial neural networks. We propose the artificial neural network (NN) architecture that can efficiently perform the nonlinear Fourier (NF) optical signal processing. The NN consists of sequential convolution layers and fully connected output layers. This NN predicts only one component of the continuous NF spectrum, such that two identical NNs have to be used to predict the real and imaginary parts of the reflection coefficient. To train the NN, we precomputed 94035 optical signals. 9403 signals were used for validation and excluded from training. The final value of the relative error for the entire validation dataset was less than 0.3%. Our findings highlight the fundamental possibility of using the NNs to analyze and process complex optical signals when the conventional algorithms can fail to deliver an acceptable result. ",
keywords = "Neural network, Nonlinear Fourier transform, Optical communication, Signal processing",
author = "Egor Sedov and Jaroslaw Prylepskiy and Igor Chekhovskoy and Sergei Turitsyn",
note = "Funding Information: E.S. and I.C. acknowledges the support from Russian Science Foundation under Grant 17-72-30006 and the support by the grant of the President of the Russian Federation (MK-677.2020.9). E.S. and S.T. are supported by the EPSRC programme grant TRANSNET, EP/R035342/1. S.T. and J.P. acknowledge the support of Leverhulme Trust project RPG-2018-063. Publisher Copyright: {\textcopyright} COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.; Applications of Machine Learning 2021 ; Conference date: 01-08-2021 Through 05-08-2021",
year = "2021",
doi = "10.1117/12.2594127",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Zelinski, {Michael E.} and Taha, {Tarek M.} and Jonathan Howe",
booktitle = "Applications of Machine Learning 2021",
address = "United States",

}

RIS

TY - GEN

T1 - Computing continuous nonlinear Fourier spectrum of optical signal with artificial neural networks

AU - Sedov, Egor

AU - Prylepskiy, Jaroslaw

AU - Chekhovskoy, Igor

AU - Turitsyn, Sergei

N1 - Funding Information: E.S. and I.C. acknowledges the support from Russian Science Foundation under Grant 17-72-30006 and the support by the grant of the President of the Russian Federation (MK-677.2020.9). E.S. and S.T. are supported by the EPSRC programme grant TRANSNET, EP/R035342/1. S.T. and J.P. acknowledge the support of Leverhulme Trust project RPG-2018-063. Publisher Copyright: © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

PY - 2021

Y1 - 2021

N2 - In this work, we demonstrate that the high-accuracy computation of the continuous nonlinear spectrum can be performed by using artificial neural networks. We propose the artificial neural network (NN) architecture that can efficiently perform the nonlinear Fourier (NF) optical signal processing. The NN consists of sequential convolution layers and fully connected output layers. This NN predicts only one component of the continuous NF spectrum, such that two identical NNs have to be used to predict the real and imaginary parts of the reflection coefficient. To train the NN, we precomputed 94035 optical signals. 9403 signals were used for validation and excluded from training. The final value of the relative error for the entire validation dataset was less than 0.3%. Our findings highlight the fundamental possibility of using the NNs to analyze and process complex optical signals when the conventional algorithms can fail to deliver an acceptable result.

AB - In this work, we demonstrate that the high-accuracy computation of the continuous nonlinear spectrum can be performed by using artificial neural networks. We propose the artificial neural network (NN) architecture that can efficiently perform the nonlinear Fourier (NF) optical signal processing. The NN consists of sequential convolution layers and fully connected output layers. This NN predicts only one component of the continuous NF spectrum, such that two identical NNs have to be used to predict the real and imaginary parts of the reflection coefficient. To train the NN, we precomputed 94035 optical signals. 9403 signals were used for validation and excluded from training. The final value of the relative error for the entire validation dataset was less than 0.3%. Our findings highlight the fundamental possibility of using the NNs to analyze and process complex optical signals when the conventional algorithms can fail to deliver an acceptable result.

KW - Neural network

KW - Nonlinear Fourier transform

KW - Optical communication

KW - Signal processing

UR - http://www.scopus.com/inward/record.url?scp=85118261503&partnerID=8YFLogxK

UR - https://elibrary.ru/item.asp?id=47520078

U2 - 10.1117/12.2594127

DO - 10.1117/12.2594127

M3 - Conference contribution

AN - SCOPUS:85118261503

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Applications of Machine Learning 2021

A2 - Zelinski, Michael E.

A2 - Taha, Tarek M.

A2 - Howe, Jonathan

PB - SPIE

T2 - Applications of Machine Learning 2021

Y2 - 1 August 2021 through 5 August 2021

ER -

ID: 34537291