Standard

Neural Networks for Nonlinear Fourier Spectrum Computation. / Sedov, Egor; Freire, Pedro J.; Chekhovskoy, Igor et al.

2021 European Conference on Optical Communication, ECOC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 European Conference on Optical Communication, ECOC 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Harvard

Sedov, E, Freire, PJ, Chekhovskoy, I, Turitsyn, S & Prilepsky, J 2021, Neural Networks for Nonlinear Fourier Spectrum Computation. in 2021 European Conference on Optical Communication, ECOC 2021. 2021 European Conference on Optical Communication, ECOC 2021, Institute of Electrical and Electronics Engineers Inc., 2021 European Conference on Optical Communication, ECOC 2021, Bordeaux, France, 13.09.2021. https://doi.org/10.1109/ECOC52684.2021.9605844

APA

Sedov, E., Freire, P. J., Chekhovskoy, I., Turitsyn, S., & Prilepsky, J. (2021). Neural Networks for Nonlinear Fourier Spectrum Computation. In 2021 European Conference on Optical Communication, ECOC 2021 (2021 European Conference on Optical Communication, ECOC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ECOC52684.2021.9605844

Vancouver

Sedov E, Freire PJ, Chekhovskoy I, Turitsyn S, Prilepsky J. Neural Networks for Nonlinear Fourier Spectrum Computation. In 2021 European Conference on Optical Communication, ECOC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (2021 European Conference on Optical Communication, ECOC 2021). doi: 10.1109/ECOC52684.2021.9605844

Author

Sedov, Egor ; Freire, Pedro J. ; Chekhovskoy, Igor et al. / Neural Networks for Nonlinear Fourier Spectrum Computation. 2021 European Conference on Optical Communication, ECOC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 European Conference on Optical Communication, ECOC 2021).

BibTeX

@inproceedings{f4ab4f8f5de04c5b92dcccdb23e342e1,
title = "Neural Networks for Nonlinear Fourier Spectrum Computation",
abstract = "We demonstrate that neural networks can outperform conventional numerical nonlinear Fourier transform algorithms for processing the noise-corrupted optical signal. Applying the Bayesian hyper-parameters optimisation, we design the architecture of neural networks capable to compute nonlinear signal spectrum at low SNR more accurately than conventional algorithms.",
author = "Egor Sedov and Freire, {Pedro J.} and Igor Chekhovskoy and Sergei Turitsyn and Jaroslaw Prilepsky",
note = "Funding Information: ES and ST are supported by the EPSRC programme grant TRANSNET, EP/R035342/1. JP and ST acknowledge the support of Leverhulme Trust project RPG-2018-063. ES acknowledges the support from the Russian Science Foundation under Grant 17-72-30006, IC acknowledges the grant of the President of the Russian Federation (MK-677.2020.9). Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 European Conference on Optical Communication, ECOC 2021 ; Conference date: 13-09-2021 Through 16-09-2021",
year = "2021",
doi = "10.1109/ECOC52684.2021.9605844",
language = "English",
isbn = "9781665438681",
series = "2021 European Conference on Optical Communication, ECOC 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2021 European Conference on Optical Communication, ECOC 2021",
address = "United States",

}

RIS

TY - GEN

T1 - Neural Networks for Nonlinear Fourier Spectrum Computation

AU - Sedov, Egor

AU - Freire, Pedro J.

AU - Chekhovskoy, Igor

AU - Turitsyn, Sergei

AU - Prilepsky, Jaroslaw

N1 - Funding Information: ES and ST are supported by the EPSRC programme grant TRANSNET, EP/R035342/1. JP and ST acknowledge the support of Leverhulme Trust project RPG-2018-063. ES acknowledges the support from the Russian Science Foundation under Grant 17-72-30006, IC acknowledges the grant of the President of the Russian Federation (MK-677.2020.9). Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - We demonstrate that neural networks can outperform conventional numerical nonlinear Fourier transform algorithms for processing the noise-corrupted optical signal. Applying the Bayesian hyper-parameters optimisation, we design the architecture of neural networks capable to compute nonlinear signal spectrum at low SNR more accurately than conventional algorithms.

AB - We demonstrate that neural networks can outperform conventional numerical nonlinear Fourier transform algorithms for processing the noise-corrupted optical signal. Applying the Bayesian hyper-parameters optimisation, we design the architecture of neural networks capable to compute nonlinear signal spectrum at low SNR more accurately than conventional algorithms.

UR - http://www.scopus.com/inward/record.url?scp=85123180424&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/6ace2666-6c7f-3bc7-a398-616c90a69697/

U2 - 10.1109/ECOC52684.2021.9605844

DO - 10.1109/ECOC52684.2021.9605844

M3 - Conference contribution

AN - SCOPUS:85123180424

SN - 9781665438681

T3 - 2021 European Conference on Optical Communication, ECOC 2021

BT - 2021 European Conference on Optical Communication, ECOC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 European Conference on Optical Communication, ECOC 2021

Y2 - 13 September 2021 through 16 September 2021

ER -

ID: 35305570