Feb 21 – 22, 2022
Europe/Berlin timezone

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

Feb 22, 2022, 11:20 AM


Benigna Untermarkt 1 02826 Görlitz Germany
Invited talk Session 3


Muhammad Kasim (University of Oxford)


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.

Primary author

Muhammad Kasim (University of Oxford)


Sam M. Vinko

Presentation materials

There are no materials yet.