Active Learning

Paper accepted at npj Computational Materials!!
Our work on uncertainty-biased molecular dynamics for machine-learning interatomic potentials has been accepted at the npj Computational Materials! Great team achievement led by Viktor!!
Federico Errica
Apr 29, 2024 1 min read Research
Paper accepted at npj Computational Materials!!
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
In this paper we combine uncertainty-biased molecular dynamics with active learning to show how we can learn machine learning interatomic potential (MLIP) models that are more robust to predictions on extrapolative regions.
Viktor Zaverkin, David Holzmüller, Henrik Christiansen, Federico Errica, Francesco Alesiani, Makoto Takamoto, Mathias Niepert, Johannes Kästner
PDF Cite Code