With the recent rapid progress in the machine-learning (ML), there have emerged a new approach using the ML methods to the exchange-correlation functional of density functional theory. In this chapter, we review how the ML tools are used for this and the performances achieved recently. It is revealed that the ML, not being opposed to the analytical methods, complements the human intuition and advance the development toward the first-principles calculation with desired accuracy.
@article{arxiv.2206.15370,
title = {Development of exchange-correlation functionals assisted by machine learning},
author = {Ryo Nagai and Ryosuke Akashi},
journal= {arXiv preprint arXiv:2206.15370},
year = {2022}
}
Comments
25 pages, 2 figures, 1 table; Review draft to be submitted in Springer Nature book chapter "Machine Learning in Molecular Sciences"; comments and suggestions are welcomed