Elemental modes research featured in Journal of Chemical Physics

Author: C-CAS

Screen Shot 2019 08 13 At 8

A recent publication by John Herr, a graduate student in the Wiest group at the University of Notre Dame, describes how the use of physically meaningful feature “called “elemental modes” to represent different elements allows transfer learning and lowers computational cost, bringing chemical modeling closer to a single machine learning model that can be fine-tuned for different systems. This paper was selected as an “Editors Choice” in the Journal of Chemical Physics – Congrats to John.