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

Fast Decoupled and DC Powerflow01:24

Fast Decoupled and DC Powerflow

392
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
392
Gradient and Del Operator01:14

Gradient and Del Operator

3.8K
In mathematics and physics, the gradient and del operator are fundamental concepts used to describe the behavior of functions and fields in space. The gradient is a mathematical operator that gives both the magnitude and direction of the maximum spatial rate of change. Consider a person standing on a mountain. The slope of the mountain at any given point is not defined unless it is quantified in a particular direction. For this reason, a "directional derivative" is defined, which is a vector...
3.8K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.3K
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...
2.3K
Long-term Depression01:05

Long-term Depression

32.2K
Long-term depression, or LTD, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTD is the process of synaptic weakening that occurs over time between pre and postsynaptic neuronal connections. The synaptic weakening of LTD works in opposition to synaptic strengthening by long-term potentiation (LTP) and together are the main mechanisms that underlie learning and memory.
32.2K
Long-term Depression01:03

Long-term Depression

2.7K
Long-term depression, or LTD, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTD is the process of synaptic weakening that occurs over time between pre and postsynaptic neuronal connections. The synaptic weakening of LTD works in opposition to synaptic strengthening by long-term potentiation (LTP) and together are the main mechanisms that underlie learning and memory.
Calcium Ion Concentration Mechanism
If over...
2.7K
Associative Learning01:27

Associative Learning

818
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
818

You might also read

Related Articles

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

Sort by
Same author

Tamoxifen-induced neutropenia and leukopenia in a breast cancer patient: a case report and literature review.

Frontiers in oncology·2026
Same author

Less confidence, less forgetting: Learning with a humbler teacher in exemplar-free Class-Incremental learning.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Decoupled neural network training with re-computation and weight prediction.

PloS one·2023
Same author

Association between polymorphisms in the GSTA4 gene and risk of lung cancer: a case-control study in a Southeastern Chinese population.

Molecular carcinogenesis·2008
Same author

[Value of intraoperative fine-needle aspiration cytology and histopathologic biopsy in the diagnosis of pancreatic cancer].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2008
Same author

A new TAG-72 cancer marker peptide identified by phage display.

Cancer letters·2008
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 9, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.6K

Fully Decoupled Neural Network Learning Using Delayed Gradients.

Huiping Zhuang, Yi Wang, Qinglai Liu

    IEEE Transactions on Neural Networks and Learning Systems
    |April 9, 2021
    PubMed
    Summary
    This summary is machine-generated.

    We introduce a fully decoupled training scheme using delayed gradients (FDG) to break sequential dependencies in neural network training. This method trains network modules independently and asynchronously, achieving comparable or better results than state-of-the-art approaches.

    More Related Videos

    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

    751

    Related Experiment Videos

    Last Updated: Nov 9, 2025

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

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.6K
    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

    751

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Deep Learning

    Background:

    • Neural network training with backpropagation (BP) involves sequential dependencies: forward, backward, and update lockings.
    • These lockings limit module independence and asynchronous training, hindering scalability and efficiency.

    Purpose of the Study:

    • To propose a fully decoupled training scheme using delayed gradients (FDG) to overcome the inherent lockings in backpropagation.
    • To enable independent and asynchronous training of neural network modules using multiple workers.

    Main Methods:

    • The proposed Fully Decoupled Training scheme using Delayed Gradients (FDG) splits networks into modules for independent, asynchronous training.
    • A gradient shrinking process is introduced to mitigate the impact of stale gradients from delayed updates.

    Main Results:

    • Theoretical analysis indicates that FDG can converge to critical points under specific conditions.
    • Experiments on deep convolutional neural networks for classification demonstrate comparable or superior generalization and acceleration compared to state-of-the-art methods.
    • FDG successfully trains various networks, including extremely deep architectures like ResNet-1202, in a decoupled manner.

    Conclusions:

    • The Fully Decoupled Training scheme using Delayed Gradients (FDG) effectively breaks sequential lockings in neural network training.
    • FDG offers a viable approach for efficient and scalable training of deep neural networks, including very deep architectures.