3 citations · 3 across the 3 of their papers we have counts for
3 papers
cs.LG2025
Improved Uncertainty Quantification in Physics-Informed Neural Networks Using Error Bounds and Solution Bundles
Pablo Flores, Olga Graf, Pavlos Protopapas +1
Physics-Informed Neural Networks (PINNs) have been widely used to obtain solutions to various physical phenomena modeled as Differential Equations. As PINNs are not naturally equip…
cs.LG2022★ 3 cited
Error-Aware B-PINNs: Improving Uncertainty Quantification in Bayesian Physics-Informed Neural Networks
Olga Graf, Pablo Flores, Pavlos Protopapas +1
Physics-Informed Neural Networks (PINNs) are gaining popularity as a method for solving differential equations. While being more feasible in some contexts than the classical numeri…
cs.LG2021
Uncertainty Quantification in Neural Differential Equations
Olga Graf, Pablo Flores, Pavlos Protopapas +1
Uncertainty quantification (UQ) helps to make trustworthy predictions based on collected observations and uncertain domain knowledge. With increased usage of deep learning in vario…