mne_denoise.dss.denoisers.SkewDenoiser

class mne_denoise.dss.denoisers.SkewDenoiser

Skewness nonlinearity (FastICA ‘skew’).

Implements:

$s_{new} = s^2$

Used for extracting sources with asymmetric probability distributions. This maximizes skewness rather than kurtosis.

Examples

>>> # Use for robust ICA
>>> from mne_denoise.dss.denoisers import SkewDenoiser, beta_gauss
>>> denoiser = SkewDenoiser()
>>> dss = IterativeDSS(denoiser=denoiser, beta=beta_gauss)

References

Särelä & Valpola (2005). Section 4.2.2 “BETTER ESTIMATE FOR THE SIGNAL VARIANCE”

__init__(*args, **kwargs)

Methods

__init__(*args, **kwargs)
denoise(source)	Apply skewness ($s^2$).