Jove
Visualize
Contact Us

Related Concept Videos

Neural Circuits01:25

Neural Circuits

1.2K
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...
1.2K
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

249
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...
249
Convolution Properties II01:17

Convolution Properties II

192
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...
192
Convolution Properties I01:20

Convolution Properties I

147
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:
147

You might also read

Related Articles

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

Sort by
Same author

Embedded Hardware-Efficient Real-Time Classification With Cascade Support Vector Machines.

IEEE transactions on neural networks and learning systems·2015
Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

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

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

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

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

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

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

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

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

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

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

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

Updated: Jun 28, 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

524

Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns.

Christos Kyrkou

    IEEE Transactions on Neural Networks and Learning Systems
    |April 23, 2024
    PubMed
    Summary
    This summary is machine-generated.

    Structured Ternary Patterns (STePs) create efficient deep learning models by using static filters instead of learnable weights. This approach reduces resource demands for mobile and embedded applications, enhancing performance and lowering trainable parameters.

    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

    393
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.8K

    Related Experiment Videos

    Last Updated: Jun 28, 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

    524
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    393
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.8K

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Deep learning (DL) models, particularly Convolutional Neural Networks (ConvNets), require substantial computational resources, limiting their deployment on resource-constrained devices.
    • Efficient DL models are crucial for on-device applications and reducing training costs.
    • Current ConvNet architectures often present challenges for mobile and embedded platforms due to high resource demands.

    Purpose of the Study:

    • To develop efficient ConvNet architectures by utilizing static convolutional filters derived from Local Binary Patterns (LBPs) and Haar features.
    • To introduce Structured Ternary Patterns (STePs) as a method for generating non-learnable filters during network initialization.
    • To reduce the number of trainable parameters and memory footprint in DL models.

    Main Methods:

    • Generated static convolutional filters, termed Structured Ternary Patterns (STePs), from LBPs and Haar features.
    • Initialized ConvNet architectures with STePs instead of learnable weight parameters.
    • Evaluated the proposed approach on four image classification datasets and for unmanned aerial vehicle (UAV)-based aerial vehicle detection.

    Main Results:

    • STePs significantly reduce trainable parameters by 40%-80% while maintaining high detection accuracy.
    • Common network backbones integrated with STePs demonstrate improved efficiency and competitive classification results.
    • Custom STeP-based networks offer favorable trade-offs for on-device applications.

    Conclusions:

    • Structured Ternary Patterns (STePs) provide an effective method for creating efficient DL architectures.
    • The use of non-learnable, pre-generated filters can substantially decrease model complexity and resource requirements.
    • This research encourages further exploration of prior-based non-learnable weights for enhancing DL model efficiency without post-training modifications.