[R] SOM (Self-organizing map)

[Prof Brian Ripley]

> Date: Tue, 31 Oct 2000 11:34:26 +0100 (CET)
> From: "Uli Flenker; Raum 704" <uli at biochem.dshs-koeln.de>
> To: Jun Yan <jyan at stat.wisc.edu>
> cc: r-help at stat.math.ethz.ch
> Subject: Re: [R] SOM (Self-organizing map)
> 
> Do I remember correctly that SOMs are "self oraganizing maps" and are more
> or less identical to Kohonen networks? As far as I know there is no R
> package for that purpose. 
> 
> A widely used - at least in Germany - neural network simulator is SNNS
> (Stuttgarter Neuraonale Netze Simulator). Its available freely under a
> GNU like license from a lot of german university servers. The people who
> built it can be reached via <http://www.informatik.uni-stuttgart.de>.
> You will find executables for several platforms as well as source code and
> documentation.
> 
> SNNS also is included in a number of Linux distributions. It is in SuSE
> and it at least has been in DLD.
> 
> I used it some years ago and did not go beyond standard backpropagation
> (which can be done in R using the nnet library included in VR). So I can't
> tell you about the Kohonen capabilities. But its included in the simulator
> definetely.
 
> 
> On Mon, 30 Oct 2000, Jun Yan wrote:
> 
> > Does anyone know of any SOM library for R? or any stand alone freeware?
> > A search from google returns SOM_PAK 3.1 developed at Helsinki University
> > of Technology. Is there newer version?

I would recommend using the original Kohonen's group code in SOM_PAK
(yes, it's 3.1 AFAIK).  There's lot of variations on this theme.
My experience of SNNS is that it tends to include everything available,
at the expense of quality.

Someone did send details to S-news of (slow) S code to do this, so
you could search the S-news archives.

I did once write an R interface to SOM_PAK for a particular project,
but am not sure that I still have it.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._