Machine learning for ultrafast nonlinear photonics

Christophe Finot; Anastasiia Sheveleva; Junsong Peng; John M. Dudley; Sonia Boscolo

doi:https://doi.org/10.1109/ICLO54117.2022

Machine learning for ultrafast nonlinear photonics

Christophe Finot, Anastasiia Sheveleva, Junsong Peng, John M. Dudley, Sonia Boscolo

Aston Institute of Photonic Technologies (AiPT)

Research output: Chapter in Book/Published conference output › Chapter (peer-reviewed) › peer-review

Abstract

We review our recent progress on the application of machine-learning techniques in the field of ultrafast nonlinear fibre optics. We demonstrate that neural networks can both efficiently predict the temporal and spectral features of optical signals that are obtained after propagation in the presence of focusing and defocusing nonlinearity and solve the associated inverse problem. We also show that evolutionary algorithms can be used to control complex nonlinear dynamics of ultrafast fibre lasers.

Original language	English
Title of host publication	Proceedings of 20th International Conference Laser Optics (ICLO 2022)
Publisher	IEEE
Number of pages	1
ISBN (Electronic)	978-1-6654-6664-6
DOIs	https://doi.org/10.1109/ICLO54117.2022
Publication status	Published - Jun 2022
Event	20th International Conference Laser Optics - Saint Petersburg, Russian Federation Duration: 20 Jun 2022 → 24 Jun 2022 https://www.laseroptics.ru

Conference

Conference	20th International Conference Laser Optics
Abbreviated title	ICLO
Country/Territory	Russian Federation
City	Saint Petersburg
Period	20/06/22 → 24/06/22
Internet address	https://www.laseroptics.ru

Bibliographical note

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Access to Document

https://doi.org/10.1109/ICLO54117.2022

iclo2022
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 28.9 KB

Cite this

@inbook{f4d52557addd4c7aa25c846ff97d6642,

title = "Machine learning for ultrafast nonlinear photonics",

abstract = "We review our recent progress on the application of machine-learning techniques in the field of ultrafast nonlinear fibre optics. We demonstrate that neural networks can both efficiently predict the temporal and spectral features of optical signals that are obtained after propagation in the presence of focusing and defocusing nonlinearity and solve the associated inverse problem. We also show that evolutionary algorithms can be used to control complex nonlinear dynamics of ultrafast fibre lasers. ",

author = "Christophe Finot and Anastasiia Sheveleva and Junsong Peng and Dudley, {John M.} and Sonia Boscolo",

note = "{\textcopyright} 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 20th International Conference Laser Optics, ICLO ; Conference date: 20-06-2022 Through 24-06-2022",

year = "2022",

month = jun,

doi = "https://doi.org/10.1109/ICLO54117.2022",

language = "English",

booktitle = "Proceedings of 20th International Conference Laser Optics (ICLO 2022)",

publisher = "IEEE",

address = "United States",

url = "https://www.laseroptics.ru",

}

TY - CHAP

T1 - Machine learning for ultrafast nonlinear photonics

AU - Finot, Christophe

AU - Sheveleva, Anastasiia

AU - Peng, Junsong

AU - Dudley, John M.

AU - Boscolo, Sonia

N1 - © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2022/6

Y1 - 2022/6

N2 - We review our recent progress on the application of machine-learning techniques in the field of ultrafast nonlinear fibre optics. We demonstrate that neural networks can both efficiently predict the temporal and spectral features of optical signals that are obtained after propagation in the presence of focusing and defocusing nonlinearity and solve the associated inverse problem. We also show that evolutionary algorithms can be used to control complex nonlinear dynamics of ultrafast fibre lasers.

AB - We review our recent progress on the application of machine-learning techniques in the field of ultrafast nonlinear fibre optics. We demonstrate that neural networks can both efficiently predict the temporal and spectral features of optical signals that are obtained after propagation in the presence of focusing and defocusing nonlinearity and solve the associated inverse problem. We also show that evolutionary algorithms can be used to control complex nonlinear dynamics of ultrafast fibre lasers.

U2 - https://doi.org/10.1109/ICLO54117.2022

DO - https://doi.org/10.1109/ICLO54117.2022

M3 - Chapter (peer-reviewed)

BT - Proceedings of 20th International Conference Laser Optics (ICLO 2022)

PB - IEEE

T2 - 20th International Conference Laser Optics

Y2 - 20 June 2022 through 24 June 2022

ER -

Machine learning for ultrafast nonlinear photonics

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this