pyriemann.utils.ajd.rjd¶

pyriemann.utils.ajd.rjd(X, *, init=None, eps=1e-08, n_iter_max=1000)¶

Approximate joint diagonalization based on Jacobi angles.

This is a direct implementation of the AJD algorithm by Cardoso and Souloumiac [1] used in JADE. The code is a translation of the Matlab code provided in the author website.

Parameters:

Xndarray, shape (n_matrices, n_channels, n_channels): Set of symmetric matrices to diagonalize.
initNone | ndarray, shape (n_channels, n_channels), default=None: Initialization for the diagonalizer.
epsfloat, default=1e-8: Tolerance for stopping criterion.
n_iter_maxint, default=1000: The maximum number of iterations to reach convergence.

Returns:

Vndarray, shape (n_channels, n_channels): The diagonalizer, an orthogonal matrix.
Dndarray, shape (n_matrices, n_channels, n_channels): Set of quasi diagonal matrices.