pyriemann.geometry.mean.mean_kullback_sym¶

pyriemann.geometry.mean.mean_kullback_sym(X, sample_weight=None, **kwargs)[source]¶

Mean of SPD/HPD matrices according to Kullback-Leibler divergence.

Symmetrized Kullback-Leibler mean is the geometric mean between the Euclidean and the harmonic means [1].

Parameters:

Xndarray, shape (…, n_matrices, n, n): Set of SPD/HPD matrices.
sample_weightNone | ndarray, shape (n_matrices,), default=None: Weights for each matrix. If None, it uses equal weights.

Returns:

Mndarray, shape (…, n, n): Symmetrized Kullback-Leibler mean.

See also

gmean

Notes

Changed in version 0.12: Add support for NumPy and PyTorch.

References

[1]

Symmetric positive-definite matrices: From geometry to applications and visualization M. Moakher and P. Batchelor. Visualization and Processing of Tensor Fields, pp. 285-298, 2006