[pymvpa] How to train a SurfaceQueryEngine?

[Nick Oosterhof]

On 5 January 2015 at 20:12, Swaroop Guntupalli <swaroopgj at gmail.com> wrote:

> My use case is a bit different from the intended one. Let me know if
> this approach of using SQEs for that makes sense:
> I want to get voxels corresponding to nodes at a particular
> hop/distance from a center node (not less than or equal to that
> distance). This is similar to HollowSphere in volume searchlights. One
> approach I am thinking of is to use multiple SQEs at difference hops
> and eliminate nodes from SQE with smaller radius. I already have
> SurfaceVerticesQueryEngine with r=0, which lets me get voxels assigned
> to any particular node, so that I can quickly get all voxels
> associated with any set of nodes.
>

Yes, that could work.


>
> Since my initial email, I thought of another approach by using SVQE
> with largest radius I want and using 'center_distances' to get voxels
> at a particular distance. I am assuming those are Euclidean distances
> from center node, is that correct?


No, they are the node-to-node distance* between the center node and the
selected node (in the case of a volumetric dataset, the "selected node"
means the node associated with that voxel).

* which distance depends on the selected distance metric, so it could be
Dijkstra or Euclidean.


> Eitherway, is there a way to pass
> that 'fa' to Measure along with the dataset using standard
> Searchlight()?
>

I haven't tried it, but looking at measures/searchlight.py it seems that
that should probably work. Please let us know if you run into issues.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20150106/6cf89a51/attachment.html>