Autor:	Schmitteckert, Peter
Rok vydání:	2020
Předmět:	Condensed Matter - Disordered Systems and Neural Networks Condensed Matter - Strongly Correlated Electrons Physics - Computational Physics
Druh dokumentu:	Working Paper
DOI:	10.1140/epjs/s11734-021-00095-z
Popis:	We present an extension of reverse engineered Kohn-Sham potentials from a density matrix renormalization group calculation towards the construction of a density functional theory functional via deep learning. Instead of applying machine learning to the energy functional itself, we apply these techniques to the Kohn-Sham potentials. To this end we develop a scheme to train a neural network to represent the mapping from local densities to Kohn-Sham potentials. Finally, we use the neural network to up-scale the simulation to larger system sizes. Comment: 11 page, 7 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2008.07923 Zobrazit plný text záznamu View this record from Arxiv