I am toying with the idea of using current libraries available with SCF (Self-Consistent Field) subspace iteration codes to train an ANN (Artificial Neural Network) to solve for SCF eigenvalue problems. Are there any obvious deficiencies with this idea?

Firstly, I would like to make sure that it is possible to train an ANN to approximate an algorithm, in this case, a numerical algorithm. I would hope that the ANN would provide some speedups over the original algorithm.

Since I don't have the requisite knowledge to form the machine learning problem in a suitable and original mathematical framework, I will rely on other people's numerical codes to train an ANN to do what I'm looking to accomplish. This would be the starting point for further exploration.

  • $\begingroup$ Welcome to SciComp.SE. To make easier to understand your post would you mind adding the full-name to SCF and ANN? $\endgroup$ – nicoguaro Feb 3 at 1:40
  • $\begingroup$ Ok. I edited the original post to specify in parenthesis what the acronyms refer to. $\endgroup$ – Jonathan Feb 3 at 3:04

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.