Operators in quantum machine learning: Response properties in chemical space

The role of response operators is well established in quantum mechanics. We investigate their use for universal quantum machine learning models of response properties in molecules. After introducing a theoretical basis, we present and discuss numerical evidence based on measuring the potential energ...

Full description

Saved in:
Bibliographic Details
Published inThe Journal of chemical physics Vol. 150; no. 6; pp. 064105 - 64116
Main Authors Christensen, Anders S., Faber, Felix A., von Lilienfeld, O. Anatole
Format Journal Article
LanguageEnglish
Published United States American Institute of Physics 14.02.2019
Subjects
Artificial intelligence
Dipole moments
Electric fields
Energy measurement
Infrared spectra
Machine learning
Mathematical models
Operators
Organic chemistry
Physics
Potential energy
Properties (attributes)
Quantum mechanics
Training
Online AccessGet full text

Cover

More Information
Summary:The role of response operators is well established in quantum mechanics. We investigate their use for universal quantum machine learning models of response properties in molecules. After introducing a theoretical basis, we present and discuss numerical evidence based on measuring the potential energy’s response with respect to atomic displacement and to electric fields. Prediction errors for corresponding properties, atomic forces, and dipole moments improve in a systematic fashion with training set size and reach high accuracy for small training sets. Prediction of normal modes and infrared-spectra of some small molecules demonstrates the usefulness of this approach for chemistry.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0021-9606
1089-7690
1089-7690
DOI:10.1063/1.5053562