Machine learning for ultrafast nonlinear photonics

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

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


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 languageEnglish
Title of host publicationProceedings of 20th International Conference Laser Optics (ICLO 2022)
Number of pages1
ISBN (Electronic) 978-1-6654-6664-6
Publication statusPublished - Jun 2022
Event20th International Conference Laser Optics - Saint Petersburg, Russian Federation
Duration: 20 Jun 202224 Jun 2022


Conference20th International Conference Laser Optics
Abbreviated titleICLO
Country/TerritoryRussian Federation
CitySaint Petersburg
Internet address

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.


Dive into the research topics of 'Machine learning for ultrafast nonlinear photonics'. Together they form a unique fingerprint.

Cite this