Standard

Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices. / Pankov, Artem V.; Vatnik, Ilya D.; Sukhorukov, Andrey A.

In: Physical Review Applied, Vol. 17, No. 2, A11, 02.2022.

Research output: Contribution to journal › Article › peer-review

Harvard

Pankov, AV, Vatnik, ID & Sukhorukov, AA 2022, 'Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices', Physical Review Applied, vol. 17, no. 2, A11. https://doi.org/10.1103/PhysRevApplied.17.024011

APA

Pankov, A. V., Vatnik, I. D., & Sukhorukov, A. A. (2022). Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices. Physical Review Applied, 17(2), [A11]. https://doi.org/10.1103/PhysRevApplied.17.024011

Vancouver

Pankov AV, Vatnik ID, Sukhorukov AA. Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices. Physical Review Applied. 2022 Feb;17(2):A11. doi: 10.1103/PhysRevApplied.17.024011

Author

Pankov, Artem V. ; Vatnik, Ilya D. ; Sukhorukov, Andrey A. / Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices. In: Physical Review Applied. 2022 ; Vol. 17, No. 2.

BibTeX

@article{4c5ad4e89461435895518906d0964b06,
title = "Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices",
abstract = "We reveal that a synthetic photonic lattice based on coupled optical loops can be utilized as a feed-forward neural network for processing of optical pulse sequences in time domain. As a proof of concept, we train the optical system to restore an initial shape of the pulse train from the signal distorted due to linear dispersion in a fiber-optic link. We also show efficient training of the optical network with an intrinsic Kerr-type nonlinearity for the realization of target nonlinear transmission functions and inference functionality for the discrimination of different pulse sequences. The theoretical modeling is performed under practical conditions and can guide future experimental realizations. ",
author = "Pankov, {Artem V.} and Vatnik, {Ilya D.} and Sukhorukov, {Andrey A.}",
note = "Funding Information: This work is supported by Ministry of Education and Science of the Russian Federation (FSUS-2020-0034) and the Australian Research Council (DP190100277). We thank Dr. Oleg Sidelnikov for valuable discussions and comments. The simulation data underlying the results presented in this paper may be obtained from the authors upon reasonable request. Publisher Copyright: {\textcopyright} 2022 American Physical Society. ",
year = "2022",
month = feb,
doi = "10.1103/PhysRevApplied.17.024011",
language = "English",
volume = "17",
journal = "Physical Review Applied",
issn = "2331-7019",
publisher = "American Physical Society",
number = "2",

}

RIS

TY - JOUR

T1 - Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices

AU - Pankov, Artem V.

AU - Vatnik, Ilya D.

AU - Sukhorukov, Andrey A.

N1 - Funding Information: This work is supported by Ministry of Education and Science of the Russian Federation (FSUS-2020-0034) and the Australian Research Council (DP190100277). We thank Dr. Oleg Sidelnikov for valuable discussions and comments. The simulation data underlying the results presented in this paper may be obtained from the authors upon reasonable request. Publisher Copyright: © 2022 American Physical Society.

PY - 2022/2

Y1 - 2022/2

N2 - We reveal that a synthetic photonic lattice based on coupled optical loops can be utilized as a feed-forward neural network for processing of optical pulse sequences in time domain. As a proof of concept, we train the optical system to restore an initial shape of the pulse train from the signal distorted due to linear dispersion in a fiber-optic link. We also show efficient training of the optical network with an intrinsic Kerr-type nonlinearity for the realization of target nonlinear transmission functions and inference functionality for the discrimination of different pulse sequences. The theoretical modeling is performed under practical conditions and can guide future experimental realizations.

AB - We reveal that a synthetic photonic lattice based on coupled optical loops can be utilized as a feed-forward neural network for processing of optical pulse sequences in time domain. As a proof of concept, we train the optical system to restore an initial shape of the pulse train from the signal distorted due to linear dispersion in a fiber-optic link. We also show efficient training of the optical network with an intrinsic Kerr-type nonlinearity for the realization of target nonlinear transmission functions and inference functionality for the discrimination of different pulse sequences. The theoretical modeling is performed under practical conditions and can guide future experimental realizations.

UR - http://www.scopus.com/inward/record.url?scp=85124468777&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/975d4b4f-785e-3097-987a-ea67ff671309/

U2 - 10.1103/PhysRevApplied.17.024011

DO - 10.1103/PhysRevApplied.17.024011

M3 - Article

AN - SCOPUS:85124468777

VL - 17

JO - Physical Review Applied

JF - Physical Review Applied

SN - 2331-7019

IS - 2

M1 - A11

ER -

ID: 35539355