Centre for Mathematics, University of Coimbra - Scientific machine learning: some methods and applications

Scientific machine learning: some methods and applications

Description:

Machine learning performance has exploded since the beginning of the 2010s. In this talk, we propose to investigate what learning can bring in the context of scientific computing and approximation of PDEs. To that end, we will introduce two interesting frameworks: "physically informed learning" and "differentiable physics". Once these notions are introduced, we apply these approaches to try to improve the resolution of elliptic and hyperbolic PDE solvers.

Date:

2022-12-09

Start Time:

14:30

Speaker:

Emmanuel Franck & Victor Michel-Dansac (Inria & IRMA, Strasbourg, France)

Institution:

Inria & IRMA Strasbourg

Place:

online: https://videoconf-colibri.zoom.us/j/95962160720

Research Groups:

-Numerical Analysis and Optimization

See more:

<Main>