Re: gaussian mixture model

Dear John,

We have a new algorithm for the identification of a fuzzy classifiers
based on EM identification of gaussian mixture model.

You can find the draft manuscript of our paper 
(J. Abonyi and F. Szeifert, Supervised fuzzy clustering for the
identification of fuzzy classifiers, Pattern Recognition Letters,
24(14) 2195-2207, October 2003)
and the related MATLAB code at the homepage of our research group: 
www.fmt.vein.hu/softcomp

Best regards,

Janos


[EMAIL PROTECTED] (christian) wrote in message news:<[EMAIL PROTECTED]>...
> www.cs.waikato.ac.nz/ml/weka/
> www.r-project.org
> 
> regards,christian
> 
> 
> Jerry Harder <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>...
> > [posted and mailed]
> > 
> > John Horton <[EMAIL PROTECTED]> wrote in
> > news:[EMAIL PROTECTED]: 
> > 
> > > If this is not the correct news group for this sorry, else...
> > > 
> > > Does anyone know of a guide / site which will enable me to implement a
> > > gaussian mixture model classifier. What I need is
> > >         info on EM algorithm?
> > >         how to create initial clusters, and how to assign new vectors
> > >         to clusters 
> > > I am not very good at maths and all the stuff I have found so far is
> > > very mathematical so also.... are there any sites which enable you to
> > > become familiar with mathematical notation - I'm at a loss here :( my
> > > apologies if these questions seem dumb, but I would really appreciate
> > > a helping hand here! tia
> > > John
> > > 
> > 
> > You would more likely to get a useful response in one of the statistics 
> > groups such as sci.stat.math or sci.stat.edu.