Gaussian Process Regression for Materials and Molecules.

Deringer VL, Bartók AP, Bernstein N, Wilkins DM, Ceriotti M, Csányi G. · 2021

Read Gaussian Process Regression for Materials and Molecules. by Deringer VL, Bartók AP, Bernstein N, Wilkins DM, Ceriotti M, Csányi G. (2021) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc8391963.txt.

Description

Deringer and co-authors introduce Gaussian process regression for work on materials and molecules. This machine learning method fits atomistic properties from data. Its best-known use is building interatomic potentials in the Gaussian Approximation Potential framework.

The review explains how to build reference data and how to describe atomic settings. It then covers the regression itself and how to test if a model is sound. The method can fit plain values as well as vectors and tensors. A survey of uses shows fast growth across chemistry and materials science. The authors end with a view of where the method should go next.

Catalog record

CREATORDeringer VL, Bartók AP, Bernstein N, Wilkins DM, Ceriotti M, Csányi G.
YEAR2021
COLLECTIONPAPERS
FORMATTXT
FILE SIZE374 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC8391963

Browse the full library · About the Tower of Babel