1 code implementation • 27 Sep 2021 • Lionel Cheng, Ekhi Ajuria Illarramendi, Guillaume Bogopolsky, Michael Bauerheim, Benedicte Cuenot
As a first step, solving the 2D Poisson equation with zero Dirichlet boundary conditions using a deep neural network is investigated using multiple-scale architectures, defined in terms of number of branches, depth and receptive field.
1 code implementation • 20 Sep 2021 • Ekhi Ajuria Illarramendi, Michaël Bauerheim, Bénédicte Cuenot
To circumvent this issue, a hybrid strategy is developed, which couples a CNN with a traditional iterative solver to ensure a user-defined accuracy level.