Search Results for author: Antonio Alguacil

Found 2 papers, 1 papers with code

Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics

no code implementations • 21 Jun 2021 • Antonio Alguacil, Wagner Gonçalves Pinto, Michael Bauerheim, Marc C. Jacob, Stéphane Moreau

Accurate modeling of boundary conditions is crucial in computational physics.

Paper
Add Code

On the reproducibility of fully convolutional neural networks for modeling time-space evolving physical systems

1 code implementation • 12 May 2021 • Wagner Gonçalves Pinto, Antonio Alguacil, Michaël Bauerheim

Reproducibility of a deep-learning fully convolutional neural network is evaluated by training several times the same network on identical conditions (database, hyperparameters, hardware) with non-deterministic Graphics Processings Unit (GPU) operations.

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.