Explores equivariant structural representations in atomistic machine learning, emphasizing the importance of representing target properties in the spherical basis.
Explores atomic descriptors, emphasizing symmetry, locality, and the challenges of incorporating electrostatics in machine learning models for chemistry.
Delves into the spectral bias of polynomial neural networks, analyzing the impact on learning different frequencies and discussing experimental results.
Explores the Wigner-Eckart theorem, tensor spherical harmonics, and vector spherical harmonics, focusing on their transformation properties and applications.
