B
Bertrand Thirion
Researcher at Université Paris-Saclay
Publications - 334
Citations - 91237
Bertrand Thirion is an academic researcher from Université Paris-Saclay. The author has contributed to research in topics: Cluster analysis & Cognition. The author has an hindex of 51, co-authored 311 publications receiving 73839 citations. Previous affiliations of Bertrand Thirion include French Institute for Research in Computer Science and Automation & French Institute of Health and Medical Research.
Papers
More filters
Posted Content
Second order scattering descriptors predict fMRI activity due to visual textures
TL;DR: In this article, the second layer scattering descriptors were evaluated with respect to the predictive power of simple contour energy -the first scattering layer, and it was shown that invariant second-layer scattering coefficients better encode voxel activity, but also that well predicted voxels need not necessarily lie in known retinotopic regions.
Proceedings ArticleDOI
Social-sparsity brain decoders: faster spatial sparsity
TL;DR: In this paper, the authors introduce sparsity in the local neighborhood of each voxel with social-sparsity, a structured shrinkage operator, and find that on brain imaging classification problems, social sparsity performs almost as well as total-variation models and better than graph-net, for a fraction of the computational cost.
Adaptive multi-class Bayesian sparse regression - An application to brain activity classification
TL;DR: A novel method for regularized regression is described and applied to the prediction of a behavioural variable from brain activation images, which is robust to overfit and more adaptive than other regularization methods.
Book ChapterDOI
Accurate definition of brain regions position through the functional landmark approach
TL;DR: In this article, a fast functional landmark detection procedure was proposed, which explicitly models the spatial variability of activation foci in the observed population, and obtained more accurate results on simulations and reproducible results on a large cohort of subjects.