Introduction à la théorie des PINNs

• Bruno Després

Room: Tour 16-26 Salle 113

Tutoriel : un PINNs en partant de zéro

• Victor Michel-Dansac
• Rémi Imbach

Room: Tour 16-26 Salle 113 In this tutorial, we will illustrate the Physics-Informed Neural Network (PINN, Raissy et al, 2019) approach to approximate the solution of a physical problem modeled by a Partial Differential Equation (PDE). We will: - build a Neural Network (NN) to serve as a parameterized function uθuθ​, - use the autodiff engine to evaluate the residual of the PDE for the candidate solution uθuθ​, - train the NN (i.e. tune parameters θθ to minimize the residual of the PDE) so that uθuθ​ approximates the solution u∗u∗ of the PDE.

Présentation de la bibliothèque jinns

• Hugo Gangloff
• Nicolas Jouvin (INRAE)

Room: Tour 16-26 Salle 113 https://gitlab.com/mia_jinns/jinns

Présentation de la bibliothèque ScimBa

• Victor Michel-Dansac

Room: Tour 16-26 Salle 113 https://www.scimba.org

Tutoriel Scimba - 1ère partie

• Rémi Imbach
• Victor Michel-Dansac

Room: Tour 16-26 Salle 113 In this tutorial, we will solve a 2D Poisson PDE on an annulus with mixed boundary conditions using a Scimba PINNs

Tutoriel Scimba - 2e partie

• Victor Michel-Dansac
• Rémi Imbach

Room: Tour 16-26 Salle 113 This tutorial covers the use of some time-discrete schemes available in Scimba for solving the rotating transport problem.