Can machines learn density functionals? Past, present, and future of ML in DFT

Key Points

• Machine learning techniques improve density functional approximations, enhancing predictive power in electronic structure calculations.
• Recent developments have led to new insights and methodologies in density functional theory, impacting both materials and molecular studies.
• The review discusses common themes from various approaches in machine learning to refine density functional theory implementations.
• Future applications of machine learning in density functional theory offer exciting prospects for advancing materials science and chemistry.