[pymvpa] searchlight

[basile pinsard]

Hi MVPA experts,

I have a theoretical question that arised from recent analysis using
searchlight (either surface or voxel based):

What is the most sensible feature selection strategy between:
- a radius with variable number of features included, which will make the
different classifiers trained on different amount of dimensions;
- a fixed number of closest voxels/surface_nodes that would represent
different surface/volume/spatial_extent depending on the localization.

I had the examples with surfaces, for which I used a spherical templates
(similar to 32k surfaces in HCP dataset) transformed into subject space. I
computed the number of neighbors for each node with a fixed radius and
noted a differential sampling resolution in the brain, which somewhat
overlay with my network of interest (motor) and thus my concerns.

With voxel based searchlight, depending on masking voxels on the borders of
the mask will have less neighbors in a fixed radius sphere.

PyMVPA has only this strategy for now, but I read many papers with fixed
amount of features in Searchlight.

What do you think?

I did an ugly modification to have a temporary fixed feature number
(closest) on surface but it should be optimized:
https://github.com/bpinsard/PyMVPA/commit/1af58ea8a57882ed57059491c19d83bed43e0bce

Thanks!

basile
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20150515/85e87e19/attachment.html>