A neural-network DFT functional trained with automatic differentiation enforces the exact relation between exchange-correlation energy and potential, improving 1D two-electron calculations including dissociation.
Since the ground-state problem of the Hamiltonian H(x1,x 2) can be treated as a one- particle problem in two dimensions, the problem can be solved exactly
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.comp-ph 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
A neural-network DFT functional trained with automatic differentiation enforces the exact relation between exchange-correlation energy and potential, improving 1D two-electron calculations including dissociation.