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

Neural Circuits01:25

Neural Circuits

2.2K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.2K
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

666
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
666
Convolution Properties II01:17

Convolution Properties II

439
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
439
Convolution Properties I01:20

Convolution Properties I

372
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
372
The Role of Ion Channels in Neuronal Computation01:19

The Role of Ion Channels in Neuronal Computation

3.4K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.4K
Non-gated Ion Channels01:24

Non-gated Ion Channels

7.7K
Ion channels are specialized proteins on the plasma membrane that allow charged ions to pass down their electrochemical gradient. Their main function is to maintain the membrane potential which is critical for cell viability. These channels are either gated or non-gated and can transport more than a thousand ions within milliseconds for the cellular event to occur.
Compared to the gated ion channels, the non-gated channels, also known as leakage or passive channels, have no gating mechanism....
7.7K

You might also read

Related Articles

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

Sort by
Same author

An alternative splicing isoform of wheat TaYRG1 resistance protein activates immunity by interacting with dynamin-related proteins.

Journal of experimental botany·2022
Same author

Using Nanoindentation to Characterize the Mechanical and Creep Properties of Shale: Load and Loading Strain Rate Effects.

ACS omega·2022
Same author

Different Hemodynamic Characteristics and Resulting in Different Risks of Rupture Between Wide-Neck and Narrow-Neck Aneurysms.

Frontiers in neurology·2022
Same author

Interplay between quantum anomalous Hall effect and magnetic skyrmions.

Proceedings of the National Academy of Sciences of the United States of America·2022
Same author

The Ag-promoted α-C-H arylation of alcohols.

RSC advances·2022
Same author

Clinicopathological study of gastric schwannoma and review of related literature.

BMC surgery·2022

Related Experiment Video

Updated: Nov 20, 2025

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

801

Convolutional Neural Networks With Gated Recurrent Connections.

Jianfeng Wang, Xiaolin Hu

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |January 26, 2021
    PubMed
    Summary

    Gated Recurrent Convolutional Networks (GRCNNs) adapt neuron receptive fields using gates, improving computer vision tasks like object recognition. This overcomes limitations of standard Recurrent Convolutional Neural Networks (RCNNs) by controlling context information flow.

    Related Experiment Videos

    Last Updated: Nov 20, 2025

    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

    801

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Artificial Neural Networks

    Background:

    • Convolutional Neural Networks (CNNs) are foundational for computer vision.
    • Recurrent Convolutional Neural Networks (RCNNs) incorporate recurrent connections, inspired by biological visual systems.
    • A limitation of RCNNs is the unbounded expansion of neuron receptive fields (RFs) with increased recurrent computations, diverging from biological plausibility.

    Purpose of the Study:

    • To address the unbounded receptive field issue in RCNNs.
    • To introduce adaptive receptive fields in recurrent convolutional layers.
    • To develop a novel deep learning model, the Gated RCNN (GRCNN), for enhanced computer vision performance.

    Main Methods:

    • Introduced gating mechanisms to recurrent connections within convolutional layers.
    • Developed the Gated Recurrent Convolutional Layer (GRCL) to control context information and modulate neuron RFs.
    • Constructed a deep model, GRCNN, by stacking multiple GRCLs.

    Main Results:

    • GRCNN achieved significantly improved results compared to RCNN on object recognition, scene text recognition, and object detection tasks.
    • The adaptive RFs controlled by gates prevent unbounded expansion, aligning better with biological constraints.
    • When combined with other adaptive RF techniques, GRCNN demonstrated competitive performance against state-of-the-art models on benchmark datasets.

    Conclusions:

    • The proposed gating mechanism effectively modulates receptive fields in recurrent convolutional networks.
    • GRCNN offers a more biologically plausible and performant alternative to existing RCNN architectures.
    • GRCNN shows strong potential for advancing various computer vision applications.