arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.12877physics.chem-ph
收藏

基于轨道的精确量子机器学习表示

An orbital-based representation for accurate Quantum Machine Learning

Konstantin Karandashev, O. Anatole von Lilienfeld

摘要:

我们介绍了一种基于电子结构的表示,用于整个化合物空间的电子性质的量子机器学习(QML)。该表示是使用计算成本低廉的从头计算,并明确占电子结构的变化。我们证明了所得到的QML模型的准确性和灵活性时,应用到属性标签,如总势能,HOMO和LUMO能量,电离势,和电子亲和力,作为数据集的训练和测试条目从QM 7 b,QM 7 b-T,QM 9,和LIBE库。对于后者,我们还证明了这种方法的能力,以考虑不同的电荷和自旋多重性的分子种类,从而在QML模型,推断总势能的基础上的几何形状,电荷和自旋作为输入。

英文摘要:

We introduce an electronic structure based representation for quantum machine learning (QML) of electronic properties throughout chemical compound space. The representation is constructed using computationally inexpensive ab initio calculations and explicitly accounts for changes in the electronic structure. We demonstrate the accuracy and flexibility of resulting QML models when applied to property labels such as total potential energy, HOMO and LUMO energies, ionization potential, and electron affinity, using as data sets for training and testing entries from the QM7b, QM7b-T, QM9, and LIBE libraries. For the latter, we also demonstrate the ability of this approach to account for molecular species of different charge and spin multiplicity, resulting in QML models that infer total potential energies based on geometry, charge, and spin as input.

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。

↑