Picture for Bertrand Thirion

Bertrand Thirion

Inria, Universite Paris Saclay, CEA

Variable Importance in High-Dimensional Settings Requires Grouping

Add code
Dec 18, 2023
Figure 1 for Variable Importance in High-Dimensional Settings Requires Grouping
Figure 2 for Variable Importance in High-Dimensional Settings Requires Grouping
Figure 3 for Variable Importance in High-Dimensional Settings Requires Grouping
Figure 4 for Variable Importance in High-Dimensional Settings Requires Grouping
Viaarxiv icon

Statistically Valid Variable Importance Assessment through Conditional Permutations

Add code
Sep 14, 2023
Figure 1 for Statistically Valid Variable Importance Assessment through Conditional Permutations
Figure 2 for Statistically Valid Variable Importance Assessment through Conditional Permutations
Figure 3 for Statistically Valid Variable Importance Assessment through Conditional Permutations
Figure 4 for Statistically Valid Variable Importance Assessment through Conditional Permutations
Viaarxiv icon

Probing Brain Context-Sensitivity with Masked-Attention Generation

Add code
May 23, 2023
Figure 1 for Probing Brain Context-Sensitivity with Masked-Attention Generation
Figure 2 for Probing Brain Context-Sensitivity with Masked-Attention Generation
Viaarxiv icon

Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context

Add code
Feb 28, 2023
Figure 1 for Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context
Figure 2 for Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context
Figure 3 for Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context
Figure 4 for Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context
Viaarxiv icon

Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps

Add code
Jul 07, 2022
Figure 1 for Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps
Figure 2 for Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps
Figure 3 for Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps
Figure 4 for Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps
Viaarxiv icon

Aligning individual brains with Fused Unbalanced Gromov-Wasserstein

Add code
Jun 19, 2022
Figure 1 for Aligning individual brains with Fused Unbalanced Gromov-Wasserstein
Figure 2 for Aligning individual brains with Fused Unbalanced Gromov-Wasserstein
Figure 3 for Aligning individual brains with Fused Unbalanced Gromov-Wasserstein
Figure 4 for Aligning individual brains with Fused Unbalanced Gromov-Wasserstein
Viaarxiv icon

A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension

Add code
May 29, 2022
Figure 1 for A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension
Figure 2 for A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension
Figure 3 for A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension
Figure 4 for A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension
Viaarxiv icon

Shared Independent Component Analysis for Multi-Subject Neuroimaging

Add code
Oct 26, 2021
Figure 1 for Shared Independent Component Analysis for Multi-Subject Neuroimaging
Figure 2 for Shared Independent Component Analysis for Multi-Subject Neuroimaging
Figure 3 for Shared Independent Component Analysis for Multi-Subject Neuroimaging
Figure 4 for Shared Independent Component Analysis for Multi-Subject Neuroimaging
Viaarxiv icon

Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction

Add code
Oct 12, 2021
Figure 1 for Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction
Figure 2 for Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction
Figure 3 for Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction
Viaarxiv icon

Functional Magnetic Resonance Imaging data augmentation through conditional ICA

Add code
Jul 14, 2021
Figure 1 for Functional Magnetic Resonance Imaging data augmentation through conditional ICA
Figure 2 for Functional Magnetic Resonance Imaging data augmentation through conditional ICA
Figure 3 for Functional Magnetic Resonance Imaging data augmentation through conditional ICA
Figure 4 for Functional Magnetic Resonance Imaging data augmentation through conditional ICA
Viaarxiv icon