A4 Article in conference proceedings
Orientation Adaptive Minimal Learning Machine for Directions of Atomic Forces (2021)

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

JYU authors or editors

Pihlajamäki, Antti
Linja, Joakim
Hämäläinen, Joonas
Nieminen, Paavo
Malola, Sami
Kärkkäinen, Tommi
Häkkinen, Hannu

Publication details

All authors or editors: Pihlajamäki, Antti; Linja, Joakim; Hämäläinen, Joonas; Nieminen, Paavo; Malola, Sami; Kärkkäinen, Tommi; Häkkinen, Hannu

Parent 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

Conference:

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Place and date of conference: Bruges, Belgium (Online event), 6.-8.10.2021

eISBN: 978-2-87587-082-7

Publication year: 2021

Pages range: 529-534

Publisher: ESANN

Publication country: Belgium

Publication language: English

DOI: https://doi.org/10.14428/esann/2021.es2021-34

Persistent website address: https://www.esann.org/sites/default/files/proceedings/2021/ES2021-34.pdf

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/78423

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.

Keywords: nanosciences; molecules; atoms; machine learning

Free keywords: machine learning; molecules; atoms; force directions

Fields of science: