On Wed, Jan 18, 2012 at 11:49:07PM +0100, Andreas wrote:
> > Actually, I am not sure what FA means. For me ICA, PCA, or any
> > decomposition model is an FA. Joris, what do you have in mind in
> > particular?
> >
> >    
> Factor analysis is a decomposition with a particular
> assumption about the noise.

tl;dr (probabilistic) PCA assumes isotropic Gaussian noise, factor analysis
relaxes this to diagonal.

It has identifiability problems though -- the latent factors are only unique
up to a rotation.

------------------------------------------------------------------------------
Keep Your Developer Skills Current with LearnDevNow!
The most comprehensive online learning library for Microsoft developers
is just $99.99! Visual Studio, SharePoint, SQL - plus HTML5, CSS3, MVC3,
Metro Style Apps, more. Free future releases when you subscribe now!
http://p.sf.net/sfu/learndevnow-d2d
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to