arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.01915cond-mat.mtrl-sciphysics.chem-ph
收藏

用于机器学习的原子环境表示的灵敏度和精确度原子间势

Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials

Berk Onat, Christoph Ortner, James R. Kermode

摘要:

真实地表示化学环境对于使用机器学习方法描述材料和分子至关重要。在这里,我们提出了这些表示的系统分类,然后调查:(i)扰动的敏感性和(ii)各种原子环境表示的有效维度,并在一系列材料数据集。研究的表象包括原子中心对称函数、切比雪夫多项式对称函数、原子位置的光滑重叠、多体张量表象和原子团簇展开。在区域(i)中,我们发现在切向扰动下,没有一个原子环境表示是线性稳定的,并且对于CHSF,对于特定的扰动选择存在不稳定性,我们表明可以通过稍微重新定义表示来消除。在区域(ii)中,我们发现大多数表示可以在不损失精度的情况下显着压缩,并且进一步选择表示方法的最佳子集可以提高为给定数据集构建的回归模型的精度。

英文摘要:

Faithfully representing chemical environments is essential for describing materials and molecules with machine learning approaches. Here, we present a systematic classification of these representations and then investigate: (i) the sensitivity to perturbations and (ii) the effective dimensionality of a variety of atomic environment representations, and over a range of material datasets. Representations investigated include Atom Centred Symmetry Functions, Chebyshev Polynomial Symmetry Functions (CHSF), Smooth Overlap of Atomic Positions, Many-body Tensor Representation and Atomic Cluster Expansion. In area (i), we show that none of the atomic environment representations are linearly stable under tangential perturbations, and that for CHSF there are instabilities for particular choices of perturbation, which we show can be removed with a slight redefinition of the representation. In area (ii), we find that most representations can be compressed significantly without loss of precision, and further that selecting optimal subsets of a representation method improves the accuracy of regression models built for a given dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑