Symmetric Learning documentation

Lightweight python package for doing geometric deep learning using ESCNN. This package simply holds:

• Generic equivariant torch models and modules that are not present in ESCNN.

• Linear algebra utilities when working with symmetric vector spaces.

• Statistics utilities for symmetric random variables.

Contents:

• linalg
  • invariant_orthogonal_projector()
  • isotypic_signal2irreducible_subspaces()
  • lstsq()
• nn
  • activations
  • conv
  • disentangled
  • distributions
  • pooling
  • normalization
• models
  • EMLP
  • IMLP
• stats
  • cov()
  • var_mean()
• representation_theory
  • compute_character_table()
  • cplx_isotypic_decomposition()
  • decompose_representation()
  • escnn_representation_form_mapping()
  • field_type_to_isotypic_basis()
  • irreps_stats()
  • is_complex_irreducible()
  • isotypic_decomp_rep()
  • map_character_tables()
  • permutation_matrix()
  • sorted_jordan_canonical_form()