Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Topology-Aware Segmentation Using Discrete Morse Theory.

... International Conference on Learning Representations·2026
Same author

TOPODIFFUSIONNET: A TOPOLOGY-AWARE DIFFUSION MODEL.

... International Conference on Learning Representations·2026
Same author

Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same author

Rapid and reliable computational markers of decision-making for predicting daily smoking behavior and smoking cessation treatment outcomes.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2026
Same author

Look Hear: Gaze Prediction for Speech-directed Human Attention.

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision·2026
Same author

Psychiatric Comorbidities in Substance Use Disorders: Sex-Based Differences in a National Real-World Clinical Sample.

The American journal of psychiatry·2026

Related Experiment Video

Updated: Apr 15, 2026

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.8K

Predictive sparse modeling of fMRI data for improved classification, regression, and visualization using the

Eugene Belilovsky1, Katerina Gkirtzou2, Michail Misyrlis3

  • 1CentraleSupélec, Grande Voie des Vignes, 92295 Châtenay-Malabry, France; Inria Saclay, Campus de l'École Polytechnique, 91120 Palaiseau, France.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|April 12, 2015
PubMed
Summary

The k-support norm enhances fMRI analysis by improving prediction and stability, outperforming other sparse regularization methods. Using an absolute loss function further boosts performance in analyzing brain scans for conditions like cocaine addiction.

Keywords:
Cocaine addictionFMRIRegularizationSparsityk-Support norm

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.5K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.7K

Related Experiment Videos

Last Updated: Apr 15, 2026

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.8K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.5K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.7K

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Biostatistics

Background:

  • Functional magnetic resonance imaging (fMRI) data analysis faces the curse of dimensionality.
  • Sparse regularization techniques are crucial for managing high-dimensional data in neuroimaging.

Purpose of the Study:

  • To compare the efficacy of various sparse regularization methods for fMRI data analysis.
  • To evaluate the performance of the k-support norm against traditional techniques like LASSO and elastic net.
  • To assess the impact of different loss functions (absolute vs. squared) on predictive accuracy.

Main Methods:

  • Application of sparse regularization techniques, including ℓ1 norm (LASSO), elastic net, and k-support norm.
  • Regression and classification analyses performed on fMRI datasets.
  • Comparison of predictive performance, solution stability, and interpretability across methods.
  • Evaluation of absolute loss versus squared loss functions.

Main Results:

  • The k-support norm demonstrated superior predictive performance, stability, and interpretability in many fMRI analysis cases.
  • The absolute loss function significantly improved predictive performance for tested regularization methods compared to the squared loss.
  • fMRI scans from cocaine-addicted and healthy control subjects were analyzed.

Conclusions:

  • The k-support norm is a highly effective tool for fMRI data analysis, offering advantages over standard methods.
  • The absolute loss function provides a significant performance enhancement for sparse regularization in fMRI.
  • Findings support the clinical generalizability of the I-RISA model for cocaine addiction.