[R] nnet: Too many weights?

[kjetil@entelnet.bo]

On 15 Oct 2003 at 14:35, Tokuyasu, Taku wrote:

There is an argument to nnet setting the maximum number of weights. 
Default is 1000. I have successfully used this. 
Try
?nnet and read carefully!

Kjetil Halvorsen

> I am using library(nnet) to train up an ANN with what I believe is a
> moderately sized dataset, but R is complaining about too many weights:
> 
> ---
> > nn.1 <- nnet(t(data), targets, size = 4, rang = 0.1, decay = 5e-4, maxit =
> 200)
> Error in nnet.default(t(data), targets, size = 4, rang = 0.1, decay = 5e-04,
> : 
>         Too many (1614) weights
> > dim(targets)
> [1] 146   2
> > dim(data)  ## Note I'm using the transpose as input
> [1] 400 146
> ---
> 
> Is there a way around this?  Pointers to relevant docs/code or the source of
> the problem would be greatly appreciated.
> 
> Thanks,
> 
> _Taku
> 
> ---
> Taku A. Tokuyasu, PhD
> UCSF Cancer Center, Box 0128
> San Francisco, CA 94143-0128
> Tel: (415) 514-1530 Fax: (415) 502-3179
> Email: tokuyasu at cc.ucsf.edu
> 
> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help