Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids

HIGHLIGHTS

• who: Peter Bju00f8rn Ju00f8rgensen from the (UNIVERSITY) have published the research work: Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids, in the Journal: (JOURNAL)
• what: In the work by37 a message-passing network is used as part of the algorithm, but a new graph, representing the local neighborhood, is created for every point in space, which makes the method computationally inefficient and the model was therefore only trained on a relatively small number of points. In the invariant version of the DeepDFT model, the edge feature is the distance . . .
  

   

  

  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.