Gaussian approximation potentials: A brief tutorial introduction
Change log
Authors
Bartõk, AP
Csányi, G
Abstract
We present a swift walk-through of our recent work that uses machine learning to fit interatomic potentials based on quantum mechanical data. We describe our Gaussian Approximation Potentials (GAP) framework, discussing a variety of descriptors, how to train the model on total energies and derivatives and the simultaneous use of multiple models. We also show a small example using QUIP, the software sandbox implementation of GAP that is available for non-commercial use.
Description
Keywords
ab initio, Atomic environments, Gaussian process, Interatomic potentials, Machine learning
Journal Title
International Journal of Quantum Chemistry
Conference Name
Journal ISSN
0020-7608
1097-461X
1097-461X
Volume Title
115
Publisher
John Wiley and Sons Inc.
Publisher DOI
Sponsorship
Engineering and Physical Sciences Research Council (EP/L014742/1)
A.P.B. is supported by a Leverhulme Early Career Fellowship and the Isaac Newton Trust.
We would like to thank our referees for their comments during the revision process.