error
Kurzer Serviceunterbruch am Montag, 8. Dezember 2025, 12 bis 13 Uhr. Sie können in diesem Zeitraum keine neuen Dokumente hochladen oder bestehende Einträge bearbeiten. Das Login wird in diesem Zeitraum deaktiviert. Grund: Wartungsarbeiten // Short service interruption on Monday, December 8, 2025, 12.00 – 13.00. During this time, you won’t be able to upload new documents or edit existing records. The login will be deactivated during this time. Reason: maintenance work
 

Delayed deep learning for continuous-time dynamical systems


Author / Producer

Date

2021-01-29

Publication Type

Master Thesis

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Bridging the gap between deep learning and dynamical systems, neural ODEs are a promising approach to model continuous-time dynamical systems. Motivated by state augmentation in discrete-time models, we propose to extend the neural ODE framework to neural delay di erential equations in order to naturally capture non-Markovian e ects such as time delays or hysteresis, which are often encountered in real world applications. We demonstrate the superior performance of neural delay di erential equations on the task of modelling a partially observed oscillator in comparison with augmented neural ODEs. Moreover, we showcase robustness to observation noise, generalization over time and initial conditions, and the expressive power on more complex dynamical systems. Furthermore, a result on universal approximation is provided and the connection to delay embeddings is discussed. In an exploratory part, we discuss deep learning approaches for stability analysis of time delay systems and propose to jointly learn a dynamics model and a Lyapunov-Razumikhin function via discretization of the Razumikhin condition. The applicability of this approach is demonstrated for the task of stabilizing an inverted pendulum with delayed feedback control.

Publication status

published

External links

Editor

Contributors

Examiner : Dörfler, Florian
Examiner : Krause, A.
Examiner : Wenk, Philippe

Book title

Journal / series

Volume

Pages / Article No.

Publisher

ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09478 - Dörfler, Florian / Dörfler, Florian check_circle

Notes

Funding

Related publications and datasets