Re: [R] k-fold cross validation with neural networks

From: Uwe Ligges <ligges_at_statistik.uni-dortmund.de>
Date: Sat 18 Jun 2005 - 22:27:01 EST

Thorstensen Nicolas wrote:

> Hi !
>
> how can I do a k-fold crossvalidation with neural networks?

For "feed-forward neural networks with a single hidden layer" see package "nnet" in bundle "VR" (already installed). For "automatical" crossvalidation see, e.g., function errorest() in package "ipred".

> and how can I load matlab data files into R?

Dunno, maybe the "R.matlab" package is of any help.

Uwe Ligges

> thx in advance!
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Sat Jun 18 22:31:50 2005

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:32:50 EST