TY - JOUR

T1 - Neural network for calculating direct and inverse nonlinear Fourier transform

AU - Sedov, E. V.

AU - Чеховской, Игорь Сергеевич

AU - Prilepsky, Jaroslaw E.

N1 - The study was supported by the RF President's Grants Council (State Support to Young Russian Scientists Programme, Grant No. MK-677.2020.9) . The work of I.S. Chekhovskoy was supported by the state assignment for fundamental research FSUS-2020-0034. The work of J.E. Prilepsky was supported by the Leverhulme Trust (Project RPG-2018-063) . Publisher Copyright: © 2021 Kvantovaya Elektronika and IOP Publishing Limited

PY - 2021/12

Y1 - 2021/12

N2 - Aneural network architecture is proposed that allows a continuous nonlinear spectrum of optical signals to be predicted and an inverse nonlinear Fourier transform (NFT) to be performed for signal modulation. The average value of the relative error in predicting the continuous spectrum by the neural network when calculating the direct NFT is found to be 2.68 10−3, and the average value of the relative error in predicting the signal for the inverse NFT is 1.62 10−4.

AB - Aneural network architecture is proposed that allows a continuous nonlinear spectrum of optical signals to be predicted and an inverse nonlinear Fourier transform (NFT) to be performed for signal modulation. The average value of the relative error in predicting the continuous spectrum by the neural network when calculating the direct NFT is found to be 2.68 10−3, and the average value of the relative error in predicting the signal for the inverse NFT is 1.62 10−4.

UR - http://www.scopus.com/inward/record.url?scp=85122512670&partnerID=8YFLogxK

U2 - 10.1070/QEL17655

DO - 10.1070/QEL17655

M3 - Article

AN - SCOPUS:85122512670

VL - 51

SP - 1118

EP - 1121

JO - Quantum Electronics

JF - Quantum Electronics

SN - 1063-7818

IS - 12

ER -