Beyond brain reading: randomized sparsity and clustering to simultaneously predict and identify

Abstract : The prediction of behavioral covariates from functional MRI (fMRI) is known as brain reading. From a statistical standpoint, this challenge is a supervised learning task. The ability to predict cognitive states from new data gives a model selection criterion: prediction accu- racy. While a good prediction score implies that some of the voxels used by the classifier are relevant, one cannot state that these voxels form the brain regions involved in the cognitive task. The best predictive model may have selected by chance non-informative regions, and neglected rele- vant regions that provide duplicate information. In this contribution, we address the support identification problem. The proposed approach relies on randomization techniques which have been proved to be consistent for support recovery. To account for the spatial correlations between voxels, our approach makes use of a spatially constrained hierarchical clustering algorithm. Results are provided on simulations and a visual experiment.
Type de document :
Communication dans un congrès
Springer. NIPS 2011 MLINI Workshop, Dec 2011, Granada, Spain. pp.9-16, 2011, Machine Learning and Interpretation in Neuroimaging. 〈10.1007/978-3-642-34713-9_2〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00704875
Contributeur : Alexandre Gramfort <>
Soumis le : mercredi 6 juin 2012 - 14:17:00
Dernière modification le : jeudi 9 février 2017 - 15:47:44
Document(s) archivé(s) le : jeudi 15 décembre 2016 - 12:36:59

Fichier

paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Alexandre Gramfort, Gaël Varoquaux, Bertrand Thirion. Beyond brain reading: randomized sparsity and clustering to simultaneously predict and identify. Springer. NIPS 2011 MLINI Workshop, Dec 2011, Granada, Spain. pp.9-16, 2011, Machine Learning and Interpretation in Neuroimaging. 〈10.1007/978-3-642-34713-9_2〉. 〈hal-00704875〉

Partager

Métriques

Consultations de
la notice

1809

Téléchargements du document

198