[R] Stepmax in Neuralnet

Gábor Malomsoki gm@|om@ok|1980 @end|ng |rom gm@||@com
Tue Jan 3 11:41:18 CET 2023


thanks,
i have not tried yet, because the memory of my computer is too small, and i
have to wait for the result ca 1 day.



Am Di., 3. Jan. 2023 um 11:21 Uhr schrieb Ivan Krylov <krylov.r00t using gmail.com
>:

> On Mon, 2 Jan 2023 17:50:09 +0100
> Gábor Malomsoki <gmalomsoki1980 using gmail.com> wrote:
>
> > if i set the stepmax parameter higher then i increase the performance
> > of the neuralnet?
> > Would be my prediction more accurate?
>
> Unfortunately, it's very hard to give a good answer to this question as
> stated. If the model is underfitted, giving it more iterations might
> result in performance increase. If the model is not underfitted, giving
> it more iterations may improve its training set performance while
> worsening its ability to predict non-training samples.
>
> Have you tried it yourself?
>
> --
> Best regards,
> Ivan
>
> ______________________________________________
> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

	[[alternative HTML version deleted]]



More information about the R-help mailing list