Tutorials
We are lacking tutorials and we are working on designing them.
What do we need to cover?
- Introduce basic concepts
- function fitting: the most abstract view on the problem and the implemented solution.
Tutorials:fitting_1d_function.rst
. - neural networks: how do they enter in function fitting
- atomic structure and classical potentials: what are atomic coordinates, energy functionals, forces, stress, boundary conditions and more
intro.rst
- descriptors: what is their meaning
Tutorials:computing_descriptors.rst
.
- function fitting: the most abstract view on the problem and the implemented solution.
- High-level usage of the package
- data organization: what data pieces do we need and where do they go
- fetching atomic structure data: how to collect coordinates and energies
- normalization: demonstrate possible approaches
- energy gradients: how they assist in fitting
- beyond: charges, partial energies, Hamiltonian matrix elements: what can we fit beyond energies and how it is done
- fitting and testing: example
- using the obtained fit: how individual coordinates are turned into descriptors, propagated and differentiated for energy gradients
- Low-level usage of the package
- code organization: how the code is structured, what belong to where and how individual modules are related
- potentials and cython: how to implement your own potential/descriptor
How the above is presented?
Tutorials will be a part of the documentation.
Edited by Artem Pulkin