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