rascaline
rascaline copied to clipboard
Computing representations for atomistic machine learning
Hello, I'd like to suggest the addition of a function, to the tutorial, that performs farthest point selection for the atomic environments as one prepares for the construction of sparse...
Each of the calculators has a short docstring, but all of them are missing an example. Also, the new `AtomicComposition` one has this issue pointed out by @frostedoyster in a...
Hello, I wonder if we should switch the way we name gradients, because at the moment the metadata for the components is not so descriptive. For the positions gradients it...
This calculator was added in #147, but could be improved and integrated more with the rest of the code: - [ ] we would want to run the calculation over...
Hello, everyone! This PR is the first step in adding the 'Transformer' class to rascaline. The 'Transformer' class makes it easy to create a representation matrix when using some other...
This should be all the math we need for the LE basis
We need some calculator that can take in one or multiple splines, and compute a per atom/per structure functions summed over neighbors. $$ < n | f > = \sum_j...
This would be the entry point of most new developers, so it would need to be quite detailed.
This would be an advanced tutorial, and could even live in the developer documentation
Currently, the user needs to know a priori the output keys returned by a given calculator's `compute` function to make a valid selection using the `selected_keys` argument. This is inconvenient...