Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems
Work
Year: 2023
Type: article
Abstract: In this paper, we present a novel methodology for automatic adaptive weighting of Bayesian Physics-Informed Neural Networks (BPINNs), and we demonstrate that this makes it possible to robustly address... more
Source: Journal of Computational Physics
Institutions Université de Pau et des Pays de l'Adour, Centre National de la Recherche Scientifique, German Research Centre for Artificial Intelligence, Center for Scalable Data Analytics and Artificial Intelligence, Center for Systems Biology Dresden +4 more
Cites: 57
Cited by: 13
Related to: 10
FWCI: 2.921
Citation percentile (by year/subfield): 99.98
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: hybrid
APC paid (est): $3,750
Funders Agence Nationale de la Recherche, Bundesministerium für Bildung und Forschung, Institut Carnot Santé Animale
Grant IDS ANR-CE45-0022, , ISIFoR P450902ISI