Learning local equivariant representations for large-scale atomistic dynamics

HIGHLIGHTS

• who: Albert Musaelian from the (UNIVERSITY) have published the paper: Learning local equivariant representations for large-scale atomistic dynamics, in the Journal: (JOURNAL) of 16/06/2022
• what: The authors demonstrate parallelization with a simulation of 100 million atoms. The relative importance of these effects in describing molecules and materials is an open question, and one of the aims of this work is to explore whether many-body interactions can be efficiently captured without increasing the effective cutoff. The authors present Allegro, an equivariant deep-learning approach that retains the high accuracy of the recently . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.