Calibration of uncertainty in the active learning of machine learning force fields

Calibration of uncertainty in the active learning of machine learning force fields

FFLUX is a machine learning force field that uses the maximum expected prediction error (MEPE) active learning algorithm to improve the efficiency of model training. MEPE uses the predictive uncertainty of a Gaussian process (GP) to balance exploration and exploitation when selecting the next traini...

Full description

Bibliographic Details
Main Authors: Adam Thomas-Mitchell, Glenn Hawe, Paul L A Popelier
Format: Article
Language:English
Published: IOP Publishing 2023-01-01
Series:Machine Learning: Science and Technology
Subjects:
machine learning force fields
Gaussian process
calibration
active learning
uncertainty quantification
Online Access:https://doi.org/10.1088/2632-2153/ad0ab5

Internet

https://doi.org/10.1088/2632-2153/ad0ab5

Similar Items