-
Notifications
You must be signed in to change notification settings - Fork 586
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
New dataset and example for decoding data #1506
Comments
Great idea! I'm happy to help contribute. Here is a start using a different toolbox. |
I'm happy to try out this one. |
First straightforward decoding example for 503 is here : And here for 504. In both cases, a very straightforward decoding approach seems to yield acceptable results. I'll focus on collection 503 as it's the one that yields the largest number of images.
Suggestions regarding where to go from here :
Any thoughts ? |
On Sat, Nov 18, 2017 at 04:57:03AM +0000, Nicolas Farrugia wrote:
Suggestions regarding where to go from here :
• Implement an example with the full regression over the rating values (using
Lasso as in the paper ? )
• Implement an example with Searchlight
• Implement an example with SpaceNetClassifier / SpaceNetRegressor
• Generate a smaller list of images that correspond a subset of subjects and
feed it to the Neurovault fetcher, so that the example doesn't download the
5000+ images
Any thoughts ?
In terms of examples, I'd like to consider replacing all the
mixed_gambles one: mixed_gambles doesn't work well.
And +1 for a smaller list of images in the download :)
|
Great proposition ! |
@thomasbazeille THis one might be useful for you. |
Is this still relevant today ? @GaelVaroquaux examples have probably changed quite a bit since nov 2017. Do you think we should design an example using a neurovault collection, maybe using a small subset of one large collection, and use the resampling feature ? |
Is this still relevant today ?
I think that what's most missing currently is an example where we run a
first-level and then do decoding on top of that.
The situation with regards to datasets and examples is however that we
are now very resource limited, as the CI takes forever to run and the
example downloads are brittle :(
|
It exists already https://github.com/nilearn/nilearn/blob/master/examples/07_advanced/plot_haxby_block_classification.py |
I wasn't happy with it, because it's a block design while I get a lot of
questions on event design. However, I agree that you are right, and that
it is good enough.
We should add more pointers to this example across the documentation
(including in the decoding tutorial).
|
The images from the following paper:
http://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.1002180
are available on
https://neurovault.org/collections/503/
and on
http://neurovault.org/collections/504/
and the emotion and pain ratings are available as meta data.
We could build an example that decodes emotion or pain using the neurovault dowloader. It would be super cool because it would add a decoding example with a different dataset (everybody is bored of Haxby, and the Jimura doesn't work well.
The text was updated successfully, but these errors were encountered: