Fork me on GitHub
Arraymancer Technical reference Tutorial Spellbook (How-To's) Under the hood

Module stats

Search:
Group by:

Procs

proc covariance_matrix[T: SomeReal](x, y: Tensor[T]): Tensor[T]
Input:
  • 2 tensors of shape [Nb observations, features]
    Note: contrary to Numpy default each row is an observations while
    echo column represent a feature/variable observed.
Returns:
  • The unbiased covariance (normalized by the number of observations - 1) in the shape [features, features]
  Source Edit