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

Reducing Line Loss01:18

Reducing Line Loss

255
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 in...
255
Survival Tree01:19

Survival Tree

245
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
245
Neuroplasticity01:01

Neuroplasticity

1.1K
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
1.1K
Weighted Mean00:57

Weighted Mean

6.0K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
6.0K
Differential Leveling01:12

Differential Leveling

494
Differential leveling is a precise method in surveying used to determine the elevation difference between two points. Its primary goal is to establish accurate vertical measurements to create level surfaces or grade lines critical for designing and constructing infrastructures such as roads, bridges, and buildings.The procedure for differential leveling begins with setting up and leveling the instrument at a point where the benchmark can be seen. The level rod is held on the benchmark (BM), and...
494
Neural Regulation01:37

Neural Regulation

41.8K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
41.8K

You might also read

Related Articles

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

Sort by
Same author

A K-Band Four-Channel Beamformer with Temperature Compensation Based on 65 nm CMOS Process.

Micromachines·2026
Same author

Secure color image encryption using a fractional-order chaotic PRNG and DNA-level operations.

Scientific reports·2026
Same author

A 6-18 GHz High-Efficiency GaN Power Amplifier Using Transistor Stacking and Reactive Matching.

Micromachines·2026
Same author

Failure Mode and Effects Analysis on the Air System of an Aero Turbofan Engine Using the Gaussian Model and Evidence Theory.

Entropy (Basel, Switzerland)·2023
Same author

A new basic probability assignment generation and combination method for conflict data fusion in the evidence theory.

Scientific reports·2023
Same author

Environmental Stability Design of the Aerial Mapping Camera Based on Multi-Dimensional Compound Structure.

Sensors (Basel, Switzerland)·2023

Related Experiment Videos

Differential Evolution Based Layer-Wise Weight Pruning for Compressing Deep Neural Networks.

Tao Wu1, Xiaoyang Li1, Deyun Zhou1

  • 1School of Electronics and Information, Northwestern Polytechnical University, 127 West Youyi Road, Xi'an 710072, China.

Sensors (Basel, Switzerland)
|February 2, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a differential evolutionary layer-wise weight pruning method to compress deep neural networks for resource-limited platforms. The novel approach optimizes pruning sensitivity per layer, significantly reducing model size while maintaining performance.

Keywords:
differential evolutionneural network compressionsparse networkweight pruning

Related Experiment Videos

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Deep neural networks (DNNs) are increasingly complex, leading to high computational and resource demands.
  • This complexity hinders deployment on resource-constrained platforms like sensors.
  • Existing model compression techniques often lack layer-specific optimization.

Purpose of the Study:

  • To develop an efficient method for compressing DNNs tailored for resource-limited environments.
  • To address the challenge of varying pruning requirements across different network layers.
  • To improve the feasibility of deploying advanced deep learning models on edge devices.

Main Methods:

  • Propose a differential evolutionary layer-wise weight pruning method.
  • Analyze pruning sensitivity for each layer individually.
  • Employ an optimization model to determine optimal pruning sensitivity sets for layers.
  • Utilize differential evolution for population-based optimization.
  • Implement a connection recovery strategy during fine-tuning.

Main Results:

  • Achieved significant compression ratios: 24x for LeNet-300-100, 14x for LeNet-5, 29x for AlexNet, and 12x for VGG16.
  • Demonstrated the effectiveness of the layer-wise pruning approach through experimental validation.
  • Successfully reduced model size while preserving network capacity.

Conclusions:

  • The proposed differential evolutionary layer-wise weight pruning method effectively compresses DNNs.
  • This technique enables the deployment of complex models on resource-limited platforms.
  • The layer-specific optimization and recovery strategy enhance model compression efficiency.