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

236
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...
236
Neuroplasticity01:01

Neuroplasticity

1.1K
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
1.1K

You might also read

Related Articles

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

Sort by
Same author

Split stoma with delayed anastomosis may be preferred for 2-stage surgical resection in high-risk patients with Crohn's disease.

Surgery·2021
Same author

Radiocontrast agent and intraductal pressure promote the progression of post-ERCP pancreatitis by regulating inflammatory response, cellular apoptosis, and tight junction integrity.

Pancreatology : official journal of the International Association of Pancreatology (IAP) ... [et al.]·2021
Same author

Occurrence and fate of polycyclic aromatic hydrocarbons from electronic waste dismantling activities: A critical review from environmental pollution to human health.

Journal of hazardous materials·2021
Same author

ATG16L2 overexpression is associated with a good prognosis in colorectal cancer.

Journal of gastrointestinal oncology·2021
Same author

A Novel Pyroptosis-Related Gene Signature for Prognostic Prediction of Head and Neck Squamous Cell Carcinoma.

International journal of general medicine·2021
Same author

Application of dermal regenerative template in reconstructing skin defects after plantar malignant melanoma excision.

Journal of B.U.ON. : official journal of the Balkan Union of Oncology·2021
Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026
Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: Nov 17, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K

StructADMM: Achieving Ultrahigh Efficiency in Structured Pruning for DNNs.

Tianyun Zhang, Shaokai Ye, Xiaoyu Feng

    IEEE Transactions on Neural Networks and Learning Systems
    |February 15, 2021
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a unified framework for structured weight pruning in deep neural networks (DNNs), significantly increasing model compression and GPU acceleration without accuracy loss. The new method achieves higher pruning rates and faster inference speeds for various DNN models.

    More Related Videos

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    650
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    792

    Related Experiment Videos

    Last Updated: Nov 17, 2025

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.7K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    650
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    792

    Area of Science:

    • Deep learning and neural network optimization.
    • Computer vision and model compression techniques.
    • High-performance computing and hardware acceleration.

    Background:

    • Deep neural networks (DNNs) require substantial computational and storage resources.
    • Existing weight pruning methods offer limited compression and acceleration, especially without accuracy loss.
    • Structured pruning methods aim to improve hardware utilization but face limitations.

    Purpose of the Study:

    • To develop a systematic framework for structured weight pruning in DNNs.
    • To enable various sparsity types (filterwise, channelwise, shapewise, non-structured).
    • To achieve higher pruning rates and GPU acceleration while maintaining or minimally impacting accuracy.

    Main Methods:

    • A unified framework combining stochastic gradient descent (SGD/ADAM) with alternating direction method of multipliers (ADMM).
    • Dynamic regularization with analytically updated targets per iteration.
    • Progressive, multi-step pruning with network purification and unused path removal.

    Main Results:

    • Achieved significant speedups (e.g., 2.58x-3.65x on AlexNet without accuracy loss).
    • Demonstrated higher speedups (3.15x-8.52x) with minimal accuracy loss (2%), including 15.0x compression.
    • Reported an unprecedented 54.2x structured pruning rate on ResNet-18 (CIFAR-10), yielding 7.6x mobile GPU speedup.

    Conclusions:

    • The proposed framework effectively enhances structured weight pruning for DNNs.
    • It overcomes previous limitations in pruning rate and GPU acceleration.
    • The method offers substantial model compression and inference speedup across different hardware platforms.