Impact of filtering on photonic time-delay reservoir computing - CNRS - Centre national de la recherche scientifique
Article Dans Une Revue Chaos: An Interdisciplinary Journal of Nonlinear Science Année : 2023

Impact of filtering on photonic time-delay reservoir computing

G. Danilenko
A. Kovalev
E. Viktorov
A. Locquet
D. Citrin
D. Rontani

Résumé

We analyze the modification of the computational properties of a time-delay photonic reservoir computer with a change in its feedback bandwidth. For a reservoir computing configuration based on a semiconductor laser subject to filtered optoelectronic feedback, we demonstrate that bandwidth selection can lead to a flat-topped eigenvalue spectrum for which a large number of system frequencies are weakly damped as a result of the attenuation of modulational instability by feedback filtering. This spectral configuration allows for the optimization of the reservoir in terms of its memory capacity, while its computational ability appears to be only weakly affected by the characteristics of the filter.
Fichier principal
Vignette du fichier
ForHAL-Filtered_feedback_in_delay_based_reservoir_computing.pdf (1.93 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03943772 , version 1 (17-01-2023)

Identifiants

Citer

G. Danilenko, A. Kovalev, E. Viktorov, A. Locquet, D. Citrin, et al.. Impact of filtering on photonic time-delay reservoir computing. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2023, 33 (1), pp.013116. ⟨10.1063/5.0127661⟩. ⟨hal-03943772⟩
54 Consultations
210 Téléchargements

Altmetric

Partager

More