Logo der Universität Basel

Research Database / FORSCHUNGSDATENBANK 
PRINTDOC
 
Publication 4657668 | Verified
 

Data Entry: Please note that the research database will be replaced by UNIverse by the end of October 2023. Please enter your data into the system https://universe-intern.unibas.ch. Thanks

Login for users with Unibas email account...

Login for registered users without Unibas email account...

 
Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions
JournalArticle (Originalarbeit in einer wissenschaftlichen Zeitschrift)
 
ID 4657668
Author(s) Parsaeifard, Behnam; Goedecker, Stefan
Author(s) at UniBasel Goedecker, Stefan
Year 2022
Title Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions
Journal Journal of Chemical Physics
Volume 156
Number 3
Pages / Article-Number 034302
Abstract Atomic fingerprints are commonly used for the characterization of local environments of atoms in machine learning and other contexts. In this work, we study the behavior of two widely used fingerprints, namely, the smooth overlap of atomic positions (SOAP) and the atom-centered symmetry functions (ACSFs), under finite changes of atomic positions and demonstrate the existence of manifolds of quasi-constant fingerprints. These manifolds are found numerically by following eigenvectors of the sensitivity matrix with quasi-zero eigenvalues. The existence of such manifolds in ACSF and SOAP causes a failure to machine learn four-body interactions, such as torsional energies that are part of standard force fields. No such manifolds can be found for the overlap matrix (OM) fingerprint due to its intrinsic many-body character.
Publisher AIP Publishing
ISSN/ISBN 0021-9606 ; 1089-7690
edoc-URL https://edoc.unibas.ch/92223/
Full Text on edoc Restricted
Digital Object Identifier DOI 10.1063/5.0070488
PubMed ID http://www.ncbi.nlm.nih.gov/pubmed/35065570
ISI-Number 000747696400015
Document type (ISI) Journal Article
 
   

MCSS v5.8 PRO. 0.363 sec, queries - 0.000 sec ©Universität Basel  |  Impressum   |    
03/05/2024