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

Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

441
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...
441
Acceleration Vectors01:30

Acceleration Vectors

10.5K
In everyday conversation, accelerating means speeding up. Acceleration is a vector in the same direction as the change in velocity, Δv, therefore the greater the acceleration, the greater the change in velocity over a given time. Since velocity is a vector, it can change in magnitude, direction, or both. Thus acceleration is a change in speed or direction, or both. For example, if a runner traveling at 10 km/h due east slows to a stop, reverses direction, and continues their run at 10 km/h...
10.5K
Convolution Properties II01:17

Convolution Properties II

292
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
292
Convolution Properties I01:20

Convolution Properties I

245
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:
245
Deconvolution01:20

Deconvolution

264
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
264
Upsampling01:22

Upsampling

329
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...
329

You might also read

Related Articles

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

Sort by
Same author

TTQR: A Traffic- and Thermal-Aware Q-Routing for 3D Network-on-Chip.

Sensors (Basel, Switzerland)·2022
Same author

An Accelerator Design Using a MTCA Decomposition Algorithm for CNNs.

Sensors (Basel, Switzerland)·2020
Same author

Expression of tissue factor pathway inhibitor-2 in gastric stromal tumor and its clinical significance.

Experimental and therapeutic medicine·2014
Same author

Facile access to cytocompatible multicompartment micelles with adjustable Janus-cores from A-block-B-graft-C terpolymers prepared by combination of ROP and ATRP.

Colloids and surfaces. B, Biointerfaces·2014
Same author

Functional layers for Zn(II) ion detection: from molecular design to optical fiber sensors.

The journal of physical chemistry. B·2013
Same author

Expression of the 78 kD glucose-regulated protein is induced by endoplasmic reticulum stress in the development of hepatopulmonary syndrome.

Gene·2013

Related Experiment Video

Updated: Sep 20, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

530

Towards Convolutional Neural Network Acceleration and Compression Based on Simonk-Means.

Mingjie Wei1, Yunping Zhao1, Xiaowen Chen1

  • 1The College of Computer Science, National University of Defence Technology, Changsha 410000, China.

Sensors (Basel, Switzerland)
|June 10, 2022
PubMed
Summary

This study introduces Simon k-means for efficient Convolutional Neural Network (CNN) model compression. The novel approach significantly reduces hardware resource usage and multiply-accumulate operations in CNN accelerators.

Keywords:
convolutional neural networksdeep learningk-meansmodel compressionweight quantization

More Related Videos

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K

Related Experiment Videos

Last Updated: Sep 20, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

530
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Convolutional Neural Networks (CNNs) are essential for image classification and target recognition but require significant computational resources.
  • Model compression is crucial for deploying CNNs on embedded devices, yet traditional retraining methods are time-consuming and can reduce precision.
  • Existing compression techniques often struggle to balance efficiency with performance, especially for hardware acceleration.

Purpose of the Study:

  • To propose a novel model compression approach for CNNs that supports hardware acceleration.
  • To introduce an extended k-means algorithm, Simon k-means, for clustering neural network weights.
  • To reduce hardware resource consumption in data movement and storage for compressed CNNs.

Main Methods:

  • Developed an extension algorithm named Simon k-means, based on the simple k-means clustering algorithm.
  • Applied Simon k-means to cluster trained weights in convolutional and fully connected layers of CNNs.
  • Implemented a data storage and index approach to minimize hardware resource consumption.
  • Designed and provided a hardware implementation of the compressed CNN accelerator.

Main Results:

  • Achieved a compression ratio of 5.27× in AlexNet on the FASHION-MNIST dataset.
  • Reduced multiply-accumulate (MAC) operations by 74.3%.
  • Demonstrated the effectiveness of the Simon k-means approach for CNN model compression and hardware acceleration.

Conclusions:

  • The proposed Simon k-means based model compression technique offers significant efficiency gains for CNNs.
  • This method effectively reduces computational complexity and hardware resource requirements, making CNNs more suitable for embedded systems.
  • The hardware implementation validates the practical applicability of the compression scheme for real-world applications.