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

Extraction: Partition and Distribution Coefficients01:14

Extraction: Partition and Distribution Coefficients

2.5K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
2.5K
Discrete Fourier Transform01:15

Discrete Fourier Transform

320
The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
320
Continuous -time Fourier Transform01:11

Continuous -time Fourier Transform

339
The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...
339
Properties of Fourier Transform II01:24

Properties of Fourier Transform II

243
The Fourier Transform (FT) is an essential mathematical tool in signal processing, transforming a time-domain signal into its frequency-domain representation. This transformation elucidates the relationship between time and frequency domains through several properties, each revealing unique aspects of signal behavior.
The Frequency Shifting property of Fourier Transforms highlights that a shift in the frequency domain corresponds to a phase shift in the time domain. Mathematically, if x(t) has...
243
Reducing Line Loss01:18

Reducing Line Loss

173
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
173
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

288
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...
288

You might also read

Related Articles

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

Sort by
Same author

The efficacy and safety of endoscopic submucosal dissection compared with endoscopic mucosal resection for colorectal tumors: a meta-analysis.

International journal of colorectal disease·2015
Same author

An imaging-guided platform for synergistic photodynamic/photothermal/chemo-therapy with pH/temperature-responsive drug release.

Biomaterials·2015
Same author

Potential Molecular Mechanisms Involved in 5-Aminolevulinic Acid-Based Photodynamic Therapy against Human Hypertrophic Scars.

Plastic and reconstructive surgery·2015
Same author

Complete Genome Sequence of a Porcine Endogenous Retrovirus Isolated from a Bama Minipig in Guangxi, Southern China.

Genome announcements·2015
Same author

The methodology of locating painful responsible vertebrae in osteoporotic vertebral compression fractures.

International journal of clinical and experimental medicine·2015
Same author

Diagnosis and treatment of perineal endometriosis: review of 17 cases.

Archives of gynecology and obstetrics·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

Related Experiment Video

Updated: Jul 16, 2025

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

33.8K

TECO: A Unified Feature Map Compression Framework Based on Transform and Entropy.

Yubo Shi, Meiqi Wang, Tianyu Cao

    IEEE Transactions on Neural Networks and Learning Systems
    |September 13, 2023
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces the Transform and Entropy-based COmpression (TECO) scheme to reduce power consumption in deep neural networks (DNNs) by compressing feature maps. TECO significantly improves compression ratios across various tasks without sacrificing model accuracy.

    More Related Videos

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    42.9K
    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

    Published on: April 13, 2013

    42.7K

    Related Experiment Videos

    Last Updated: Jul 16, 2025

    Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
    11:15

    Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

    Published on: June 27, 2013

    33.8K
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    42.9K
    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

    Published on: April 13, 2013

    42.7K

    Area of Science:

    • Computer Science
    • Electrical Engineering
    • Artificial Intelligence

    Background:

    • Deep neural networks (DNNs) face significant power consumption challenges due to massive memory accesses of feature maps (FMs).
    • This energy bottleneck limits the efficiency of DNN accelerators.

    Purpose of the Study:

    • To propose a unified framework, the Transform and Entropy-based COmpression (TECO) scheme, for efficient FM compression during DNN inference.
    • To explore and leverage the unimodal distribution characteristic in the frequency domain of FMs.

    Main Methods:

    • Developed a hardware-friendly coding scheme exploiting the unimodal distribution of FM frequency spectra.
    • Utilized information entropy theory to create a novel loss function for enhancing compression ratios and comparing compressors.
    • Implemented and tested the TECO scheme on ResNet-50, UNet, and Yolo-v4 models.

    Main Results:

    • Achieved high compression ratios: [specific ratios] on ResNet-50 (image classification), UNet (dark image enhancement), and Yolo-v4 (object detection).
    • Demonstrated significant compression ratio improvements of 21%, 157%, and 152% compared to original FMs across the tested models.
    • Maintained model accuracy after compression.

    Conclusions:

    • The TECO scheme offers an effective solution for compressing FMs in DNNs, addressing power consumption bottlenecks.
    • The novel approach successfully balances high compression ratios with preserved model accuracy.
    • TECO's hardware-friendly design and entropy-based loss function provide a versatile framework for DNN acceleration.