no code implementations • 6 Feb 2024 • Aik Rui Tan, Johannes C. B. Dietschreit, Rafael Gomez-Bombarelli
Generating a data set that is representative of the accessible configuration space of a molecular system is crucial for the robustness of machine learned interatomic potentials (MLIP).
1 code implementation • 2 May 2023 • Aik Rui Tan, Shingo Urata, Samuel Goldman, Johannes C. B. Dietschreit, Rafael Gómez-Bombarelli
In this work, we examine multiple UQ schemes for improving the robustness of NN interatomic potentials (NNIPs) through active learning.
2 code implementations • 27 Jan 2021 • Daniel Schwalbe-Koda, Aik Rui Tan, Rafael Gómez-Bombarelli
Neural network (NN) interatomic potentials provide fast prediction of potential energy surfaces, closely matching the accuracy of the electronic structure methods used to produce the training data.