Machine learning for ultrafast nonlinear fibre photonics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Machine learning for ultrafast nonlinear fibre photonics

Résumé

We provide an overview of our latest advances in the application of machine learning methods to ultrafast nonlinear fibre optics. We establish that neural networks are capable of accurately forecasting the temporal and spectral properties of optical signals that are obtained after propagation in the focusing or defocusing regimes of nonlinearity. Machine learning is also efficient in addressing the related inverse problem as well as providing insights into the underlying physical process. In addition, we illustrate the use of evolutionary algorithms to access and optimise complex nonlinear dynamics of ultrafast fibre lasers.
Fichier principal
Vignette du fichier
ICTON_Finot_JMD_SB.pdf (295.15 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04659384 , version 1 (23-07-2024)

Identifiants

  • HAL Id : hal-04659384 , version 1

Citer

Christophe Finot, Sonia Boscolo, Junsong Peng, Andrei Ermolaev, Anastasiia Sheveleva, et al.. Machine learning for ultrafast nonlinear fibre photonics. 24rd International Conference on Transparent Optical Networks (ICTON), Jul 2024, Bari (IT), Italy. ⟨hal-04659384⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More