MxNE sparse inverse solver. More...

#include <inv_mxne.h>

Static Public Member Functions
static InvMxneResult	compute (const Eigen::MatrixXd &matGain, const Eigen::MatrixXd &matData, double alpha, int nIterations=50, double tolerance=1e-6)

Detailed Description

MxNE sparse inverse solver.

Mixed-Norm Estimate (MxNE) sparse inverse solver.

Minimizes: ||M - G*X||^2_F + alpha * sum_i ||X_i||_2 using an Iteratively Reweighted Least Squares (IRLS) approach for the L21-norm (group lasso).

Definition at line 85 of file inv_mxne.h.

Member Function Documentation

InvMxneResult InvMxne::compute	(	const Eigen::MatrixXd &	matGain,
		const Eigen::MatrixXd &	matData,
		double	alpha,
		int	nIterations = 50,
		double	tolerance = 1e-6 )

static

Compute the MxNE inverse solution.

Parameters

[in]	matGain	Forward gain matrix (n_channels x n_sources).
[in]	matData	Measurement data (n_channels x n_times).
[in]	alpha	Regularization parameter.
[in]	nIterations	Maximum number of IRLS iterations.
[in]	tolerance	Convergence tolerance on weight change.

Definition at line 59 of file inv_mxne.cpp.

The documentation for this class was generated from the following files: