Improving the predictive capability of molecular properties in ab initio
simulations is essential for advanced material discovery. Despite recent
progress making use of machine learning, utilizing deep neural networks to
improve quantum chemistry modelling remains severely limited by the scarcity
and heterogeneity of appropriate experimental data. Here we show how training a
neural network to replace the exchange-correlation functional within a
fully-differentiable three-dimensional Kohn-Sham density functional theory
(DFT) framework can greatly improve simulation accuracy. Using only eight
experimental data points on diatomic molecules, our trained
exchange-correlation networks enable improved prediction accuracy of
atomization energies across a collection of 104 molecules containing new bonds
and atoms that are not present in the training dataset.

本文通过使用神经网络替代密度泛函理论中的交换 - 相关泛函来提高模拟精度，表明此方法可通过少量的实验数据点来处理包含新键和原子的化合物集合。（Keywords translated to: ab initio 模拟、机器学习、神经网络、量子化学建模、原子化能）

使用全可微密度泛函理论从自然界学习交换相关泛函

Learning the exchange-correlation functional from nature with fully  differentiable density functional theory

We introduce a machine learning model to predict atomization energies of a
diverse set of organic molecules, based on nuclear charges and atomic positions
only. The problem of solving the molecular Schr\"odinger equation is mapped
onto a non-linear statistical regression problem of reduced complexity.
Regression models are trained on and compared to atomization energies computed
with hybrid density-functional theory. Cross-validation over more than seven
thousand small organic molecules yields a mean absolute error of ~10 kcal/mol.
Applicability is demonstrated for the prediction of molecular atomization
potential energy curves.

我们引入了一个机器学习模型来预测有机分子的原子化能，基于核电荷和原子位置。该回归模型是通过将求解分子 Schr"odinger 方程的问题映射为复杂度较低的非线性统计回归问题。我们使用杂化密度泛函理论计算的原子化能进行回归模型的训练和比较。通过对超过七千个小有机分子进行交叉验证，得到的平均绝对误差为～10 kcal/mol。该模型的适用性已经通过预测分子原子化潜能曲线得到证明。