extraction of derivative of hidden layers w.r.t symmetry function

CompPhysVienna / n2p2

n2p2 - A Neural Network Potential Package

https://compphysvienna.github.io/n2p2/

GNU General Public License v3.0

214 stars 81 forks source link

extraction of derivative of hidden layers w.r.t symmetry function #193

Open shubhamdongriyal opened 10 months ago

shubhamdongriyal commented 10 months ago

Hi, I am trying to get access to the derivatives of neurons in hidden layers w.r.t symmetry function (dLdG) in n2p2. Is there a way to extract that information? If not, could anyone direct me where the changes need to be made to get those?