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

Weighted Mean00:57

Weighted Mean

5.3K
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...
5.3K
Design Example: Aggregate Gradation01:24

Design Example: Aggregate Gradation

149
The right type and quality of aggregates are crucial for concrete as they significantly influence its properties, mix proportions, and cost-effectiveness. If different sources are available for sand, the commonly used fine aggregate in concrete, the selection of sand is primarily based on its gradation.
The grading, or particle-size distribution, of sand is determined using sieve analysis, with standard sizes ranging from 150 μm to 10 mm (ASTM No. 100 sieve to 3⁄8 in. sieve). Sand is...
149
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

136
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
136
Reducing Line Loss01:18

Reducing Line Loss

196
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...
196
Downsampling01:20

Downsampling

257
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...
257
Uniform Depth Channel Flow: Problem Solving01:18

Uniform Depth Channel Flow: Problem Solving

128
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
128

You might also read

Related Articles

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

Sort by
Same author

Fine-Grained Enhancement Convolutional Diffusion Transformer for Unsupervised Anomaly Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

An Efficient Regenerated Cross-Modal Hashing: Improving Existing Hash Codes with the Arbitrary Length.

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

Adapting Domain-Aware Knowledge to Vision-Language Model for Zero-Shot Anomaly Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Predefined-Time Dynamic Self-Triggered Approximate Optimal Control of Autonomous Surface Vehicles With Disturbances.

IEEE transactions on cybernetics·2025
Same author

RaLo: Rank-aware low-rank adaptation for pre-trained foundation models.

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

Central similarity joint-learning for cross-domain retrieval.

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

Related Experiment Video

Updated: Sep 16, 2025

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
07:05

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

2.7K

Gradient aware adaptive quantization: Locally uniform quantization with learnable clipping thresholds for globally

Kang Zhou1, Yuning Qiu2, Yuhang Li1

  • 1School of Automation, Guangdong University of Technology, Guangzhou 510006, China.

Neural Networks : the Official Journal of the International Neural Network Society
|July 11, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a new non-uniform quantization method for neural network compression. It improves model performance by adaptively learning quantization levels and clipping thresholds, reducing errors.

Keywords:
Learnable clipping thresholdNeural networkNon-uniform quantization

Related Experiment Videos

Last Updated: Sep 16, 2025

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
07:05

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

2.7K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Non-uniform quantization enhances neural network compression by adapting to weight distributions.
  • Traditional methods suffer performance degradation due to reliance on weight density alone.

Purpose of the Study:

  • To develop an advanced non-uniform quantization technique for improved neural network compression.
  • To address the performance limitations of existing non-uniform quantization methods.

Main Methods:

  • A novel non-uniform quantization approach is proposed, featuring adaptive quantization levels and automatic clipping threshold learning.
  • A local uniform quantization strategy refines quantization in dense weight regions.
  • Weight gradients are incorporated for optimal quantization level assignment.
  • A learnable, linear interpolation-based clipping method minimizes outlier impact.

Main Results:

  • The proposed method significantly reduces quantization error.
  • Validated on CIFAR10, CIFAR100, Tiny-ImageNet, and ImageNet100 datasets.
  • Demonstrates improved model performance post-quantization compared to traditional methods.

Conclusions:

  • The novel non-uniform quantization method effectively reduces quantization errors and enhances model performance.
  • Adaptive learning of clipping thresholds and quantization levels is crucial for efficient neural network compression.