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

Downsampling01:20

Downsampling

157
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
157
¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)01:20

¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)

1.1K
When proton-coupled carbon-13 spectra are simplified by a broadband proton decoupling technique, structural information about the coupled protons is lost. Distortionless enhancement by polarization transfer (DEPT) is a technique that provides information on the number of hydrogens attached to each carbon in a molecule. While the DEPT experiment utilizes complex pulse sequences, the pulse delay and flip angle are specifically manipulated. The resulting signals have different phases depending on...
1.1K
Convolution Properties I01:20

Convolution Properties I

149
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:
149
Upsampling01:22

Upsampling

236
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
236
Fast Fourier Transform01:10

Fast Fourier Transform

319
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log⁡2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
319
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

195
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
195

You might also read

Related Articles

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

Sort by
Same author

Bacillus Subtilis THC1I Restores Intestinal Barrier Integrity and Gut Microbiota Balance in a Mouse Model of Antibiotic-Associated Diarrhea.

Current microbiology·2026
Same author

Dynamic chain for scheduling of the multi-AGV systems with load-aware motion profiling.

Scientific reports·2026
Same author

Coupled Tensor Decomposition for Compact Network Representation.

IEEE transactions on neural networks and learning systems·2025
Same author

Singular values-driven automated filter pruning.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

RRT-CS: A free-collision planner for capsule-like SCORBOT by iterated learning.

PloS one·2025
Same author

Design and implementation of a field robot using a parallelogram mechanism.

Science progress·2024
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
Same journal

Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

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

cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

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

Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

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

Related Experiment Video

Updated: Jul 1, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

399

Enhanced Network Compression Through Tensor Decompositions and Pruning.

Van Tien Pham, Yassine Zniyed, Thanh Phuong Nguyen

    IEEE Transactions on Neural Networks and Learning Systems
    |March 8, 2024
    PubMed
    Summary
    This summary is machine-generated.

    We introduce NORTON, a network compression method combining tensor decomposition and pruning. NORTON enhances model efficiency and accuracy by using filter decomposition and structured pruning.

    More Related Videos

    Diffusion Tensor Magnetic Resonance Imaging in Chronic Spinal Cord Compression
    07:00

    Diffusion Tensor Magnetic Resonance Imaging in Chronic Spinal Cord Compression

    Published on: May 7, 2019

    8.9K
    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
    09:47

    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

    Published on: December 15, 2023

    1.0K

    Related Experiment Videos

    Last Updated: Jul 1, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    399
    Diffusion Tensor Magnetic Resonance Imaging in Chronic Spinal Cord Compression
    07:00

    Diffusion Tensor Magnetic Resonance Imaging in Chronic Spinal Cord Compression

    Published on: May 7, 2019

    8.9K
    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
    09:47

    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

    Published on: December 15, 2023

    1.0K

    Area of Science:

    • Artificial Intelligence
    • Computer Vision
    • Deep Learning

    Background:

    • Network compression is crucial for deploying deep learning models on resource-constrained devices.
    • Combining tensor decomposition and pruning offers synergistic benefits for network compression.
    • Existing methods may not fully exploit the advantages of both tensor decomposition and pruning.

    Purpose of the Study:

    • To propose a novel network compression method, NORTON (Network cOmpRession through TensOr decompositions and pruNing).
    • To enhance network compression by integrating filter decomposition with structured pruning.
    • To demonstrate the effectiveness of NORTON across various network architectures and tasks.

    Main Methods:

    • NORTON employs filter decomposition to analyze network weights in detail.
    • A novel structured pruning approach is integrated with the decomposed model.
    • Experiments were conducted on diverse architectures, datasets, and computer vision tasks.

    Main Results:

    • NORTON achieves superior performance compared to state-of-the-art (SOTA) compression techniques.
    • The method demonstrates significant improvements in model complexity reduction.
    • Accuracy is maintained or improved, showcasing the effectiveness of the compression strategy.

    Conclusions:

    • NORTON offers an effective approach to network compression by combining tensor decomposition and pruning.
    • The proposed filter decomposition and structured pruning integration yields significant benefits.
    • NORTON represents a valuable contribution to efficient deep learning model deployment.