Celebrating two years and having fun with machine-learned DFT functionals

It's two years since my first post. Yay! This first post was about the performance of some recently developed DFT functionals on the relative energy between the singlet and quintet of two metal complexes. So, why not celebrate the birthday of my blog by doing this, again? But this time, which functional? Introducing the so-called machine-learning …

Machine-learning + DLPNO-CCSD(T) = ?

Note: try to read this like “As seen on TV” You try to do a calculation for a protein, but it is too big? Your publication is rejected because a nasty referee required a method better than DFT? Fear no more, introducing the revolutionary “Outsmarting quantum chemistry through transfer learning” by Smith et al. In …