Semantic Scholar Open Access 2020 601 sitasi

The MLIP package: moment tensor potentials with MPI and active learning

I. Novikov Konstantin Gubaev E. Podryabinkin A. Shapeev

Lihat Sumber DOI

Abstrak

The subject of this paper is the technology (the ‘how’) of constructing machine-learning interatomic potentials, rather than science (the ‘what’ and ‘why’) of atomistic simulations using machine-learning potentials. Namely, we illustrate how to construct moment tensor potentials using active learning as implemented in the MLIP package, focusing on the efficient ways to automatically sample configurations for the training set, how expanding the training set changes the error of predictions, how to set up ab initio calculations in a cost-effective manner, etc. The MLIP package (short for Machine-Learning Interatomic Potentials) is available at https://mlip.skoltech.ru/download/.

Topik & Kata Kunci

Physics Computer Science

Penulis (4)

I. Novikov

Konstantin Gubaev

E. Podryabinkin

A. Shapeev

Format Sitasi

APA MLA BibTeX

Novikov, I., Gubaev, K., Podryabinkin, E., Shapeev, A. (2020). The MLIP package: moment tensor potentials with MPI and active learning. https://doi.org/10.1088/2632-2153/abc9fe

Akses Cepat

Lihat di Sumber doi.org/10.1088/2632-2153/abc9fe

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Total Sitasi: 601×
Sumber Database: Semantic Scholar
DOI: 10.1088/2632-2153/abc9fe
Akses: Open Access ✓