Back to Search
Start Over
Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments.
- Source :
-
Journal of chemical theory and computation [J Chem Theory Comput] 2021 Oct 12; Vol. 17 (10), pp. 6658-6670. Date of Electronic Publication: 2021 Sep 29. - Publication Year :
- 2021
-
Abstract
- Artificial neural networks (NNs) are one of the most frequently used machine learning approaches to construct interatomic potentials and enable efficient large-scale atomistic simulations with almost ab initio accuracy. However, the simultaneous training of NNs on energies and forces, which are a prerequisite for, e.g., molecular dynamics simulations, can be demanding. In this work, we present an improved NN architecture based on the previous GM-NN model [Zaverkin V.; Kästner, J. J. Chem. Theory Comput . 2020, 16, 5410-5421], which shows an improved prediction accuracy and considerably reduced training times. Moreover, we extend the applicability of Gaussian moment-based interatomic potentials to periodic systems and demonstrate the overall excellent transferability and robustness of the respective models. The fast training by the improved methodology is a prerequisite for training-heavy workflows such as active learning or learning-on-the-fly.
Details
- Language :
- English
- ISSN :
- 1549-9626
- Volume :
- 17
- Issue :
- 10
- Database :
- MEDLINE
- Journal :
- Journal of chemical theory and computation
- Publication Type :
- Academic Journal
- Accession number :
- 34585927
- Full Text :
- https://doi.org/10.1021/acs.jctc.1c00527