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

Uncertainty: Overview00:59

Uncertainty: Overview

In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
Uncertainty: Confidence Intervals00:54

Uncertainty: Confidence Intervals

The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor 't,' or...
Propagation of Uncertainty from Random Error00:59

Propagation of Uncertainty from Random Error

An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
Propagation of Uncertainty from Systematic Error01:10

Propagation of Uncertainty from Systematic Error

The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this particular...
Uncertainty in Measurement: Accuracy and Precision03:37

Uncertainty in Measurement: Accuracy and Precision

Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
Prediction Intervals01:03

Prediction Intervals

The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
The...

You might also read

Related Articles

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

Sort by
Same author

The impact of sound intervention on sleep quality and stress levels in college students: a randomized controlled trial.

Frontiers in psychology·2026
Same author

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026
Same author

Hierarchical Consistency Learning for Test-Time Adaptation in Camouflage Perception.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Ecological and health risk assessment of soil metal(loid)s based on machine learning approaches.

Journal of hazardous materials·2026
Same author

Knowledge Diffusion-Based Adaptive Alignment with Hierarchical Context for Video Temporal Grounding.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Graph Rotation Network: Equivariant Graph Neural Network for Efficient Inverse Design in 4-D Printing.

IEEE transactions on neural networks and learning systems·2026

Related Experiment Videos

Reliable Uncertainty Estimation via Discriminative Feature Learning for Evidential Deep Classification.

Linye Li, Yufei Chen, Xiaodong Yue

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |July 13, 2026
    PubMed
    Summary

    Evidential Deep Learning (EDL) struggles with complex classification tasks. Tangential Gradient Descent (TGD) enhances feature learning for better uncertainty estimation and scalability in deep learning models.

    Related Experiment Videos

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computer Vision

    Background:

    • Evidential Deep Learning (EDL) quantifies uncertainty using Dirichlet distributions.
    • Current EDL methods focus on calibrating distributions, often neglecting feature representations.
    • Feature representations are crucial for both classification performance and uncertainty estimation.

    Purpose of the Study:

    • To investigate the impact of feature representations on EDL performance.
    • To address the limitations of existing EDL approaches in learning discriminative features, especially with increasing class numbers.
    • To propose a novel method for improving feature learning in EDL for enhanced uncertainty estimation.

    Main Methods:

    • A feature-centric approach is adopted to analyze the relationship between evidence and features.
    • Tangential Gradient Descent (TGD), a new feature optimization technique, is introduced.
    • TGD decomposes the loss gradient into tangential and radial components to refine feature representations.

    Main Results:

    • Existing EDL methods exhibit limitations in learning discriminative features as class numbers grow, impacting uncertainty estimation.
    • TGD promotes feature alignment to a simplex Equiangular Tight Frame (ETF), enhancing inter-class separability.
    • TGD improves the ability to differentiate between certain and uncertain samples, leading to more reliable uncertainty estimates.
    • Experiments on CIFAR-10, CIFAR-100, and ImageNet-200 show TGD outperforms conventional EDL methods in uncertainty estimation and scalability.

    Conclusions:

    • Feature representation learning is critical for effective Evidential Deep Learning.
    • Tangential Gradient Descent (TGD) offers a promising solution for improving EDL by optimizing feature learning.
    • The proposed TGD method enhances both classification performance and uncertainty estimation, demonstrating superior scalability.