Orientation Adaptive Minimal Learning Machine for Directions of Atomic Forces
Abstract
Machine learning (ML) force fields are one of the most common applications of ML in nanoscience. However, commonly these methods are trained on potential energies of atomic systems and force vectors are omitted. Here we present a ML framework, which tackles the greatest difficulty on using forces in ML: accurate prediction of force direction. We use the idea of Minimal Learning Machine to device a method which can adapt to the orientation of an atomic environment to estimate the directions of force vectors. The method was tested with linear alkane molecules.
Main Authors
Format
Conferences
Conference paper
Published
2021
Subjects
Publication in research information system
Publisher
ESANN
Original source
https://www.esann.org/sites/default/files/proceedings/2021/ES2021-34.pdf
The permanent address of the publication
https://urn.fi/URN:NBN:fi:jyu-202110295450Käytä tätä linkitykseen.
Parent publication ISBN
978-2-87587-082-7
Review status
Peer reviewed
DOI
https://doi.org/10.14428/esann/2021.es2021-34
Conference
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Language
English
Is part of publication
ESANN 2021 : Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Online event (Bruges, Belgium), October 06 - 08
Citation
- Pihlajamäki, A., Linja, J., Hämäläinen, J., Nieminen, P., Malola, S., Kärkkäinen, T., & Häkkinen, H. (2021). Orientation Adaptive Minimal Learning Machine for Directions of Atomic Forces. In ESANN 2021 : Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Online event (Bruges, Belgium), October 06 - 08 (pp. 529-534). ESANN. https://doi.org/10.14428/esann/2021.es2021-34
License
Funder(s)
Research Council of Finland
Research Council of Finland
Research Council of Finland
Funding program(s)
Academy Programme, AoF
Academy Programme, AoF
Research profiles, AoF
Akatemiaohjelma, SA
Akatemiaohjelma, SA
Profilointi, SA
Additional information about funding
This work was supported by Academy of Finland through the AIPSE research program with grant 315549 to H.H. and 315550 to T.K., through the Universities Profiling Actions with grant 311877 to T.K., and through H.H.’s Academy Professorship. Work was also supported by ”Antti ja Jenny Wihurin rahasto” via personal funding to A.P..
Copyright© Authors, 2021