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.

翻译：在初始模拟中提高分子特性的预测能力对于先进的材料发现至关重要。尽管最近利用机器学习取得了进步,但利用深神经网络改进量子化学建模仍然由于适当实验数据的稀缺性和异质性而受到严重限制。这里我们展示了如何培训神经网络,以取代在完全不同的三维Kohn-Sham密度功能理论(DFT)框架内的交换-关系功能,可以大大提高模拟准确性。我们经过培训的交换-关系网络仅利用了8个关于二解分子的实验数据点,能够提高包含培训数据集中不存在的新联结和原子的104个分子集聚在一起的消化能量的预测准确性。