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

Survival Tree01:19

Survival Tree

382
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
382
Reducing Line Loss01:18

Reducing Line Loss

353
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss in...
353
Neural Control of Respiration01:18

Neural Control of Respiration

4.5K
The neural regulation of respiration is a meticulously coordinated process primarily controlled by the respiratory centers located within the brainstem. These centers, composed of specialized neurons, transmit nerve impulses that control the contraction and relaxation of our respiratory muscles.
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
4.5K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model01:13

Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model

285
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
285
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

9.0K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
9.0K

You might also read

Related Articles

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

Sort by
Same author

Synthetic MRI Neuroimaging Correlates of Frailty: Correlations Between Frailty Scales and Brain Structural Integrity.

Aging medicine (Milton (N.S.W))·2026
Same author

Pipa Qingfei Yin Ameliorates Acne Inflammation in Mice via Suppressing Neutrophil Extracellular Traps.

Microbiology and immunology·2026
Same author

Unveiling Spin and Poynting Dual Textures of an Optical Skyrmionic Tube in Free Space.

Physical review letters·2026
Same author

Prognostic Value of Coronary Sinus Flow and Aortic Pressure Gradient Quantified by 4D Flow CMR in AMI.

Academic radiology·2026
Same author

Deep learning reconstruction for chest MRI: image quality and diagnostic agreement with CT.

European journal of radiology·2026
Same author

Multi-adaptive super-resolving pupil filter for sub-diffraction limited focusing and imaging.

Optics express·2026

Related Experiment Video

Updated: Jan 13, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

732

Progressive Feedforward Collapse of ResNet Training.

Sicong Wang, Kuo Gai, Shihua Zhang

    IEEE Transactions on Neural Networks and Learning Systems
    |October 28, 2025
    PubMed
    Summary

    Deep neural networks exhibit neural collapse (NC) in their final training phase. This study introduces progressive feedforward collapse (PFC) to explain feature collapse in intermediate layers of ResNets.

    Area of Science:

    • Deep learning theory
    • Computer vision
    • Machine learning

    Background:

    • Neural collapse (NC) describes a phenomenon in deep neural networks (DNNs) where last-layer features align with classifier vectors.
    • The behavior of intermediate layers during training and their relation to data remains underexplored.

    Purpose of the Study:

    • To investigate the geometric properties of intermediate layers in ResNets.
    • To propose and validate a new conjecture, progressive feedforward collapse (PFC), for feature collapse across network depth.
    • To develop a theoretical model for well-trained ResNets.

    Main Methods:

    • Characterization of intermediate layer geometry in ResNets.
    • Derivation of a transparent model for ResNets using Wasserstein space geodesics.

    Related Experiment Videos

    Last Updated: Jan 13, 2026

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    732
  • Proposal of a multilayer unconstrained feature model (MUFM) with optimal transport regularization.

    • Main Results:

    • The study proposes progressive feedforward collapse (PFC), suggesting collapse increases during forward propagation.
    • PFC metrics monotonically decrease with depth across various datasets.
    • The MUFM model shows feature concentration relative to input data, differing from NC.

    Conclusions:

    • The study extends neural collapse to progressive feedforward collapse (PFC) for intermediate layers.
    • PFC models the collapse phenomenon and its data dependence in DNNs.
    • This work enhances theoretical understanding of ResNets in classification tasks.