Die DPG-Frühjahrstagung in Dresden musste abgesagt werden! Lesen Sie mehr ...

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 1: AKPIK Talks

AKPIK 1.6: Vortrag

Montag, 16. März 2020, 18:00–18:15, HSZ 301

Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory — •Jonathan Schmidt, Carlos Benavides-Riveros, and Miguel Alexandre Lopes Marques — Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, 06120 Halle (Saale), Germany

We train a neural network as the universal exchange-correlation functional of density-functional theory to reproduce both the exact exchange-correlation energy and the exchange-correlation potential. By using the automatic differentiation functionality present in modern machine-learning frameworks, we impose the exact mathematical relation between the exchange-correlation energy and the potential, leading to a fully consistent method. The developed functional is extremely non-local, but retains the computational scaling of traditional local or semi-local approximations. It therefore holds the promise of solving some of the delocalization problems that plague density-functional theory, while maintaining the computational efficiency that characterizes the Kohn-Sham equations. We demonstrate the feasibility of our approach by looking at strongly-correlated one-dimensional electronic systems, where density-functional methods are known to fail, and investigate the behavior and performance of our functional by varying the degree of non-locality.