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>  
 
© Centre for Mathematics, University of Coimbra, funded by
Science and Technology Foundation
Financiado total ou parcialmente pela FCT, Fundação para a Ciência e a Tecnologia, I.P., sob o Financiamento de:
Projeto Estratégico com a referência DOI UID/00324/2025.   https://doi.org/10.54499/UID/PRR/00324/2025     UID/PRR/00324/2025   https://doi.org/10.54499/UID/PRR2/00324/2025   UID/PRR2/00324/2025
Powered by: rdOnWeb v1.4 | technical support