| 2023 | 2022 | 2021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 | 2011 | 2010 | 2009 | 2008 | 2007 | 2006 | 2005 | 2004 | 2003 | 2002 | 2001 | 2000 | 1999 | 1997
Machine Learning the Derivative Discontinuity of Density Functional Theory
Authors: Johannes Gedeon
Ref.: Master thesis, Martin-Luther University of Halle-Wittenberg (2021)
Abstract: In this thesis, we propose a way to train a neural network as the ensemble universal functional of a system of fractional electron numbers that describes correctly the derivative discontinuity and the piecewise linear behavior. The machine learning functionals we present contain explicitly the physics of the derivative discontinuity of DFT, are highly nonlocal, and are trained for systems with fractional densities.