Salvato in:
Dettagli Bibliografici
Autori principali: Monsel, Thibault, Semeraro, Onofrio, Mathelin, Lionel, Charpiat, Guillaume
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2306.14545
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917787100774400
author Monsel, Thibault
Semeraro, Onofrio
Mathelin, Lionel
Charpiat, Guillaume
author_facet Monsel, Thibault
Semeraro, Onofrio
Mathelin, Lionel
Charpiat, Guillaume
contents Discontinuities and delayed terms are encountered in the governing equations of a large class of problems ranging from physics and engineering to medicine and economics. These systems cannot be properly modelled and simulated with standard Ordinary Differential Equations (ODE), or data-driven approximations such as Neural Ordinary Differential Equations (NODE). To circumvent this issue, latent variables are typically introduced to solve the dynamics of the system in a higher dimensional space and obtain the solution as a projection to the original space. However, this solution lacks physical interpretability. In contrast, Delay Differential Equations (DDEs), and their data-driven approximated counterparts, naturally appear as good candidates to characterize such systems. In this work we revisit the recently proposed Neural DDE by introducing Neural State-Dependent DDE (SDDDE), a general and flexible framework that can model multiple and state- and time-dependent delays. We show that our method is competitive and outperforms other continuous-class models on a wide variety of delayed dynamical systems. Code is available at the repository \href{https://github.com/thibmonsel/Time-and-State-Dependent-Neural-Delay-Differential-Equations}{here}.
format Preprint
id arxiv_https___arxiv_org_abs_2306_14545
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Time and State Dependent Neural Delay Differential Equations
Monsel, Thibault
Semeraro, Onofrio
Mathelin, Lionel
Charpiat, Guillaume
Artificial Intelligence
Dynamical Systems
Discontinuities and delayed terms are encountered in the governing equations of a large class of problems ranging from physics and engineering to medicine and economics. These systems cannot be properly modelled and simulated with standard Ordinary Differential Equations (ODE), or data-driven approximations such as Neural Ordinary Differential Equations (NODE). To circumvent this issue, latent variables are typically introduced to solve the dynamics of the system in a higher dimensional space and obtain the solution as a projection to the original space. However, this solution lacks physical interpretability. In contrast, Delay Differential Equations (DDEs), and their data-driven approximated counterparts, naturally appear as good candidates to characterize such systems. In this work we revisit the recently proposed Neural DDE by introducing Neural State-Dependent DDE (SDDDE), a general and flexible framework that can model multiple and state- and time-dependent delays. We show that our method is competitive and outperforms other continuous-class models on a wide variety of delayed dynamical systems. Code is available at the repository \href{https://github.com/thibmonsel/Time-and-State-Dependent-Neural-Delay-Differential-Equations}{here}.
title Time and State Dependent Neural Delay Differential Equations
topic Artificial Intelligence
Dynamical Systems
url https://arxiv.org/abs/2306.14545