Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data - IMT Atlantique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data

Résumé

Over the last few years, several works have proposed deep learning architectures to learn dynamical systems from observation data with no or little knowledge of the underlying physics. A line of work relies on learning representations where the dynamics of the underlying phenomenon can be described by a linear operator, based on the Koopman operator theory. However, despite being able to provide reliable long-term predictions for some dynamical systems in ideal situations, the methods proposed so far have limitations, such as requiring to discretize intrinsically continuous dynamical systems, leading to data loss, especially when handling incomplete or sparsely sampled data. Here, we propose a new deep Koopman framework that represents dynamics in an intrinsically continuous way, leading to better performance on limited training data, as exemplified on several datasets arising from dynamical systems.
Fichier principal
Vignette du fichier
main.pdf (515.49 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03895087 , version 1 (12-12-2022)
hal-03895087 , version 2 (10-03-2023)

Licence

Paternité

Identifiants

Citer

Anthony Frion, Lucas Drumetz, Mauro Dalla Mura, Guillaume Tochon, Abdeldjalil Aissa El Bey. Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data. ICASSP 2023: IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes, Greece. ⟨10.1109/ICASSP49357.2023.10094919⟩. ⟨hal-03895087v2⟩
116 Consultations
225 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More