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

AI for atmosphere-ocean sciences: advancements, challenges and ways forward.

National science review·2026
Same author

Multimodal deep learning with anatomically constrained attention for screening MRI-detectable TMJ abnormalities from panoramic images.

NPJ digital medicine·2026
Same author

Lifestyle, genetic risk, plasma pTau217, and incident cognitive impairment in WRAP.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same author

Evaluating the effect of extra-cerebral off-target binding in [F-18]MK6240 PET scans in early-stage Alzheimer's disease.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

Superpixel-ComBat modeling: A joint approach for harmonization and characterization of inter-scanner variability in T1-weighted images.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

More fit KL-VS heterozygotes have more favorable AD-relevant biomarker profiles.

Alzheimer's & dementia (New York, N. Y.)·2025

Related Experiment Video

Updated: Dec 21, 2025

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy
07:55

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy

Published on: July 9, 2017

12.0K

Sampling-free Uncertainty Estimation in Gated Recurrent Units with Applications to Normative Modeling in

Seong Jae Hwang1, Ronak R Mehta1, Hyunwoo J Kim2

  • 1Dept. of Computer Sciences, Univ. of Wisconsin-Madison.

Uncertainty in Artificial Intelligence : Proceedings of the ... Conference. Conference on Uncertainty in Artificial Intelligence
|May 15, 2020
PubMed
Summary

This study introduces a novel, sampling-free method for uncertainty estimation in Gated Recurrent Units (GRUs). This approach leverages classical probabilistic network ideas for efficient and deterministic uncertainty quantification in deep learning models.

More Related Videos

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.3K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.9K

Related Experiment Videos

Last Updated: Dec 21, 2025

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy
07:55

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy

Published on: July 9, 2017

12.0K
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.3K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.9K

Area of Science:

  • Computer Science
  • Machine Learning
  • Artificial Intelligence
  • Neuroimaging

Background:

  • Growing demand for uncertainty estimation in AI systems for reliability.
  • Current Bayesian methods for deep learning uncertainty are computationally intensive.
  • Need for efficient uncertainty quantification in sequential models.

Purpose of the Study:

  • To develop a deterministic, sampling-free method for uncertainty estimation in Gated Recurrent Units (GRUs).
  • To explore the utility of uncertainty estimates in computer vision, machine learning, and neuroimaging.
  • To enable statistical analysis in deep learning neuroimaging studies using normative modeling.

Main Methods:

  • Utilized classical concepts from exponential families on probabilistic networks.
  • Applied these concepts to derive deterministic uncertainty estimates for GRUs.
  • Avoided computationally expensive sampling-based estimation techniques.

Main Results:

  • Successfully implemented a sampling-free uncertainty estimation for GRUs.
  • Demonstrated the direct quantification of uncertainty deterministically.
  • Showcased the applicability of uncertainty estimates in computer vision, machine learning, and neuroimaging.

Conclusions:

  • Classical probabilistic network ideas offer an effective starting point for GRU uncertainty estimation.
  • Deterministic, sampling-free uncertainty quantification is feasible and beneficial.
  • This method advances statistical analysis capabilities in deep learning-based neuroimaging.