Loading [a11y]/accessibility-menu.js
Neural Ordinary Differential Equations with Trainable Solvers | IEEE Conference Publication | IEEE Xplore

Neural Ordinary Differential Equations with Trainable Solvers


Abstract:

When considering the data-driven identification of non-linear differential equations, the choice of the integration scheme to use is far from being trivial and may dramat...Show More

Abstract:

When considering the data-driven identification of non-linear differential equations, the choice of the integration scheme to use is far from being trivial and may dramatically impact the identification problem. In this work, we discuss this aspect and propose a novel architecture that jointly learns Neural Ordinary Differential Equations (NODEs) as well as the corresponding integration schemes that would minimize the forecast of a given sequence of observations. We demonstrate its relevance with numerical experiments on non-linear dynamics, including chaotic systems.
Date of Conference: 14-19 April 2024
Date Added to IEEE Xplore: 18 March 2024
ISBN Information:

ISSN Information:

Conference Location: Seoul, Korea, Republic of

Funding Agency:


References

References is not available for this document.