Distance weighted self-attention for nonlocal density functional approximation by artificial neural network

Kulaev Kirill Dmitrievich, Bogdan Protsenko, Alexander Ryabov, Alexander Guda, Evgeny Burnaev, Vladimir Vanovskiy

Keywords: Density Functional Theory, Neural Networks, Machine Learning, Quantum Chemistry

TL;DR: We investigate a new architecture for exchange-correlation functional approximation and show that it is possible to efficiently account for nonlocal effects by applying the modified attention mechanism directly to an electron density grid.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 235