Second order scattering descriptors predict fMRI activity due to visual textures

Michael Eickenberg 1, 2 Fabian Pedregosa 1, 3 Senoussi Mehdi 1 Alexandre Gramfort 4, 5 Bertrand Thirion 1
1 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data
NEUROSPIN - Service NEUROSPIN, Inria Saclay - Ile de France
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Second layer scattering descriptors are known to provide good classification performance on natural quasi-stationary processes such as visual textures due to their sensitivity to higher order moments and continuity with respect to small deformations. In a functional Magnetic Resonance Imaging (fMRI) experiment we present visual textures to subjects and evaluate the predictive power of these descriptors with respect to the predictive power of simple contour energy - the first scattering layer. We are able to conclude not only that invariant second layer scattering coefficients better encode voxel activity, but also that well predicted voxels need not necessarily lie in known retinotopic regions.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-00834928
Contributor : Fabian Pedregosa <>
Submitted on : Saturday, August 10, 2013 - 11:32:28 AM
Last modification on : Thursday, March 7, 2019 - 3:34:14 PM
Long-term archiving on : Tuesday, April 4, 2017 - 11:36:35 PM

Files

prni_2013.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00834928, version 1
  • ARXIV : 1310.1257

Citation

Michael Eickenberg, Fabian Pedregosa, Senoussi Mehdi, Alexandre Gramfort, Bertrand Thirion. Second order scattering descriptors predict fMRI activity due to visual textures. PRNI 2013 - 3nd International Workshop on Pattern Recognition in NeuroImaging, Jun 2013, Philadelphia, United States. ⟨hal-00834928⟩

Share

Metrics

Record views

2332

Files downloads

333