-
Class Summary
| Class |
Description |
| Exp |
The contrast function when the independent components are highly
super-Gaussian, or when robustness is very important.
|
| Kurtosis |
The kurtosis of the probability density function of a signal.
|
| LogCosh |
A good general-purpose contrast function for ICA.
|
Package smile.projection.ica Description
The contrast functions in FastICA. Using maximum entropy approximations of
differential entropy, FastICA introduce a family of new contrast (objective)
functions for ICA. These contrast functions enable both the estimation of
the whole decomposition by minimizing mutual information, and estimation
of individual independent components as projection pursuit directions.
The contrast functions must be a non-quadratic non-linear function
that has second-order derivative.