[pymvpa] Spatiotemporal Feature Selection

Roberto Guidotti robbenson18 at gmail.com
Thu Jul 19 14:02:59 UTC 2012

Dear all,

I've another question about spatiotemporal analysis. In my dataset I have 6
runs per task with approximately a hundred volumes each task each run and
running a classification on only 6 examples is very overfitting-oriented,
how can I do to reduce the overfitting? I've tried with a leave 3 run out
crossvalidation in order to have more testing runs and a very general model
fitted only on 3 runs (I use SVM)? Are there some other strategies?

Thank you,

On 19 July 2012 13:01, Roberto Guidotti <robbenson18 at gmail.com> wrote:

> Dear all,
> I'm working on spatiotemporal analysis of fMRI data, in this case the
> number of features increases drammatically and I want to perform a Feature
> Selection.
> In the toolbox the Feature Selection of event related datasets is done
> watching the spatiotemporal features variation across condition or checking
> the single feature. I think it could be useful to select voxels that
> temporally varies across experiment.
> It is possible to perform a sort of spatiotemporal feature selection, if
> not yet implemented? Or I'm asking a question theoretically wrong?
> Thank you
> Roberto.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20120719/92bc3075/attachment.html>

More information about the Pkg-ExpPsy-PyMVPA mailing list