Repulsive ensembles of physics-informed neural networks with repulsion in the joint space of function values and equation parameters give uncertainty estimates closer to the Bayesian posterior than standard ensembles.
Physics-informed neural network ( PINN ) evolution and beyond: A systematic literature review and bibliometric analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks
Repulsive ensembles of physics-informed neural networks with repulsion in the joint space of function values and equation parameters give uncertainty estimates closer to the Bayesian posterior than standard ensembles.