A tutorial on how to build neural networks for potential energy surfaces of molecules. It was made for a lecture on active learning, as part of a course on scientific computing for molecular physics course by Andrey Yachmenev in university of Hamburg. The codes are based on [1], and the accompanying codes.
If you use the code, please cite:
[1] Y. Saleh, V. Sanjay, A. Iske, A. Yachmenev, and J. Küpper , Active learning of potential-energy surfaces of weakly bound complexes with regression-tree ensembles, J. Chem. Phys. 155, 144109 (2021).