Search Results for author: Håkon Noren

Found 2 papers, 2 papers with code

Date Published Github Stars

Learning Dynamical Systems from Noisy Data with Inverse-Explicit Integrators

1 code implementation • 6 Jun 2023 • Håkon Noren, Sølve Eidnes, Elena Celledoni

We introduce the mean inverse integrator (MII), a novel approach to increase the accuracy when training neural networks to approximate vector fields of dynamical systems from noisy data.

1
Paper
Code

Learning Hamiltonian Systems with Mono-Implicit Runge-Kutta Methods

1 code implementation • 7 Mar 2023 • Håkon Noren

Numerical integrators could be used to form interpolation conditions when training neural networks to approximate the vector field of an ordinary differential equation (ODE) from data.

0
Paper
Code
Cannot find the paper you are looking for? You can Submit a new open access paper.
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy