📢 Featured article: Synergy of ML and semiempirical models

Exciting news! Our article “Synergy of semiempirical models and machine learning in computational chemistry” has been featured on the front cover of the September issue of the Journal of Chemical Physics. Moreover, it is open-acess!

I am thrilled to see how ML enhances old-school quantum mechanics. Note the need for new flexible optimization tools and datasets was marked by James Stewart, Mr. Mopac, back in 2002. Many of his conclusions could be easily taken for excerpts from modern ML papers.

The lesson learned from this experience, an important lesson painfully learned, was that the composition of the reference data set is of paramount importance.

Finally, as more and more elements are parameterized, and as methods become increasingly sophisticated, the transition will have to be made to a purely mathematical approach.

Title: “Synergy of semiempirical models and machine learning in computational chemistry”
Author: Nikita Fedik. Full cover composed by AIP Publishing.
Source: The Journal of Chemical Physics, 159
License: CC BY