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

Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Parallel Resonance01:23

Parallel Resonance

558
The parallel RLC circuit is an arrangement where the resistor (R), inductor (L), and capacitor (C) are all connected to the same nodes and, as a result, share the same voltage across them. The parallel RLC circuit is analyzed in terms of admittance (Y), which reflects the ease with which current can flow. The admittance is given by:
558
Parallel Processing01:20

Parallel Processing

716
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
716
Network Covalent Solids02:18

Network Covalent Solids

16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
Resistors In Parallel01:23

Resistors In Parallel

6.2K
Resistors are in parallel when one end of all the resistors are connected to a continuous wire of negligible resistance and the other end of all the resistors are also connected to one another through a continuous wire of negligible resistance. In the case of a parallel configuration, the potential drop across each resistor is the same. Current through each resistor can be found using Ohm’s law, I = V/R, where the voltage is constant across each resistor. The sum of the individual currents...
6.2K
Series and Parallel Capacitors01:14

Series and Parallel Capacitors

9.4K
Capacitors, fundamental components in electronic circuits, can be connected in series and/or parallel configurations. Each configuration has different impacts on the overall behavior of the circuit.
First, consider capacitors connected in series to a battery. In this configuration, the plate connected to the battery's positive terminal develops a positive charge, while the plate attached to the negative terminal becomes negatively charged. An equal magnitude of charge is induced on the...
9.4K

You might also read

Related Articles

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

Sort by
Same author

Heterogeneous Multi-Task Learning With Expert Diversity.

IEEE/ACM transactions on computational biology and bioinformatics·2022
Same author

Structured Label Inference for Visual Understanding.

IEEE transactions on pattern analysis and machine intelligence·2019
Same author

Validation of accuracy of SVM-based fall detection system using real-world fall and non-fall datasets.

PloS one·2017
Same author

Multi-Instance Classification by Max-Margin Training of Cardinality-Based Markov Networks.

IEEE transactions on pattern analysis and machine intelligence·2017
Same author

A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials.

Medical & biological engineering & computing·2016
Same author

Distinguishing the causes of falls in humans using an array of wearable tri-axial accelerometers.

Gait & posture·2013
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Jan 31, 2026

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Deep Neural Network Compression by In-Parallel Pruning-Quantization.

Frederick Tung, Greg Mori

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 19, 2018
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces CLIP-Q, a novel deep network compression algorithm. CLIP-Q jointly prunes and quantizes networks in parallel, improving efficiency for resource-constrained systems.

    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

    1.1K
    A Neonatal Mouse Spinal Cord Compression Injury Model
    13:31

    A Neonatal Mouse Spinal Cord Compression Injury Model

    Published on: March 27, 2016

    13.2K

    Related Experiment Videos

    Last Updated: Jan 31, 2026

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

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.0K
    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

    1.1K
    A Neonatal Mouse Spinal Cord Compression Injury Model
    13:31

    A Neonatal Mouse Spinal Cord Compression Injury Model

    Published on: March 27, 2016

    13.2K

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Deep neural networks (DNNs) achieve high accuracy in visual recognition.
    • Increasingly complex DNNs challenge deployment on resource-limited devices.
    • Efficient computation is crucial for deploying DNNs across various platforms.

    Purpose of the Study:

    • To develop a deep network compression algorithm for efficient DNN deployment.
    • To jointly perform weight pruning and quantization in parallel with fine-tuning.
    • To overcome limitations of sequential pruning and quantization methods.

    Main Methods:

    • Proposed CLIP-Q (Compression Learning by In-Parallel Pruning-Quantization) algorithm.
    • Jointly performs weight pruning and quantization in parallel with network fine-tuning.
    • Leverages complementary nature of pruning and quantization to recover from errors.

    Main Results:

    • CLIP-Q significantly improves state-of-the-art network compression on benchmarks like ImageNet.
    • Achieved state-of-the-art compression on various architectures including AlexNet, VGGNet, GoogLeNet, and ResNet.
    • Demonstrated effectiveness with efficient architectures (MobileNet, ShuffleNet) and non-convolutional networks (memory networks).

    Conclusions:

    • CLIP-Q offers a superior approach to deep network compression.
    • The method enhances deployment of DNNs on resource-constrained systems.
    • CLIP-Q is versatile, applicable to diverse network architectures and tasks.