A link to the notebook (I've done it in Google Colab) so you can properly see the images and the rest of the content.

In the "Gifs with examples" file you can see the results of training the neural network on various probability density functions coresponding to the electron in the hydrogen atom. Each gif has the name labeled in the form n-l-m, where n, l and m are the principal, azimuthal and magnetic quantum numbers, respectively. I have trained the model between 2000 and 4000 samples per iteration, 5 to 8 hours.

All the references are included in the Google Colab notebook.

Citation

If you find this repository useful, please cite the following:

@misc{Bodnar2022SCHDCNF,
  author = {Bodnar, Andrei},
  title = {Schrodinger-Continuous-Normalizing-Flows},
  year = {2022},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/AndreiB137/Schrodinger-Continuous-Normalizing-Flows}},
}

Licence