Deep learning and the Schrödinger equation

From National Research Council Canada

Download
  1. (PDF, 2 MB)
DOIResolve DOI: https://doi.org/10.1103/PhysRevA.96.042113
AuthorSearch for: 1 ; Search for: 1 ; Search for: 1 
Name affiliation
  1. National Research Council Canada. Security and Disruptive Technologies
FormatText
TypeArticle
Journal titlePhysical Review A
ISSN2469-9926
2469-9934
Volume96
Issue4
Abstract
We have trained a deep (convolutional) neural network to predict the ground-state energy of an electron in four classes of confining two-dimensional electrostatic potentials. On randomly generated potentials, for which there is no analytic form for either the potential or the ground-state energy, the model was able to predict the ground-state energy to within chemical accuracy, with a median absolute error of 1.49 mHa. We also investigated the performance of the model in predicting other quantities such as the kinetic energy and the first excited-state energy.
Publication date
PublisherAmerican Physical Society
Related Data
LanguageEnglish
Peer reviewedYes
NPARC number23002689
Export citationExport as RIS
Report a correctionReport a correction
Record identifier672e419f-a979-4a7a-8ed5-bcfa4586d306
Record created2017-12-20
Record modified2019-12-23
Date modified:
Report a problem on this page