Software development for atomistic learning

In COSMO we develop software to make atomistic simulations via machine learning easier. In particular, we are currently working on the following projects:

  • Equistore: a specialized data storage format for all your atomistic machine learning needs, and more. Think numpy ndarray or pytorch Tensor equipped with extra metadata for atomic — and other particles — systems. You can find scopes and core concepts here.
  • Numerical optimization (smooth basis optimization / improving the spherical harmonics recursively, Wigner kernel)