期刊
MACHINE LEARNING-SCIENCE AND TECHNOLOGY
卷 2, 期 2, 页码 -出版社
IOP Publishing Ltd
DOI: 10.1088/2632-2153/abc9fe
关键词
machine-learning interatomic potentials; active learning; ab initio calculations
类别
资金
- Russian Science Foundation [18-13-00479]
- Russian Science Foundation [18-13-00479] Funding Source: Russian Science Foundation
This paper focuses on the technology of constructing machine-learning interatomic potentials through active learning in the MLIP package, addressing efficient methods for automatically sampling training sets, the impact of expanding training sets on prediction errors, and cost-effective setup of ab initio calculations. The MLIP package can be downloaded at https://mlip.skoltech.ru/download/.
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/.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据