With the recent rapid progress in the machine-learning (ML), there have emerged a new approach using the ML methods for developing the exchange-correlation functionals 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 human intuition and advances the development of the first-principles calculation with desired accuracy.
CITATION STYLE
Nagai, R., & Akashi, R. (2023). Development of Exchange-Correlation Functionals Assisted by Machine Learning. In Challenges and Advances in Computational Chemistry and Physics (Vol. 36, pp. 91–112). Springer Science and Business Media B.V. https://doi.org/10.1007/978-3-031-37196-7_4
Mendeley helps you to discover research relevant for your work.