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 Experiment Videos

A learning algorithm for oscillatory cellular neural networks.

C Y. Ho1, H Kurokawa

  • 1Department of Electronic Engineering, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Correction: Why did we encounter a pCRM-positive specimen whose preoperative MRI indicates negative mesorectal fascia involvement in middle to low rectal cancer?

Techniques in coloproctology·2025
Same author

Why did we encounter a pCRM-positive specimen whose preoperative MRI indicates negative mesorectal fascia involvement in middle to low rectal cancer?

Techniques in coloproctology·2025
Same author

Evaluation of Color-matching Ability of a Structural Colored Resin Composite.

Operative dentistry·2021
Same author

Flexural Properties and Polished Surface Characteristics of a Structural Colored Resin Composite.

Operative dentistry·2021
Same author

Total ankle arthroplasty incorporating a total talar prosthesis: a comparative study against the standard total ankle arthroplasty.

The bone & joint journal·2019
Same author

Application of the Self- Assembling Peptide P11-4 for Prevention of Acidic Erosion.

Operative dentistry·2018
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel cellular oscillatory neural network for temporal segregation of stationary patterns. The model achieves global synchronization and temporal segregation of image segments using a simplified design and a unique learning rule, reducing hardware complexity.

Area of Science:

  • Computational Neuroscience
  • Artificial Neural Networks
  • Image Processing

Background:

  • Temporal segregation of stationary patterns is crucial for image processing.
  • Traditional oscillatory neural networks can be complex and prone to errors.
  • Cellular neural networks offer local connectivity for feature extraction.

Purpose of the Study:

  • To present a novel cellular type oscillatory neural network for temporal segregation.
  • To simplify the dynamics and reduce hardware implementation complexity.
  • To achieve global synchronization and temporal segregation of image segments.

Main Methods:

  • An array of locally connected neural oscillators with a 4-connected neighborhood.
  • A novel learning rule and initialization scheme for global synchronization.

Related Experiment Videos

  • Oscillators composed of two mutually coupled neurons with piecewise-linear activation functions.
  • Special grouping synapses for temporal segregation of overlapping segments.

    • Main Results:

    • Global synchronization achieved without erroneous synchrony among uncorrelated objects.
    • Demonstrated temporal segregation of overlapping gray-level and color segments.
    • The proposed learning rule circumvents component mismatches, facilitating large-scale integration.

    Conclusions:

    • The cellular oscillatory neural network architecture has significant application potential for temporal segregation.
    • The simplified dynamics and learning rule reduce hardware complexity and improve robustness.
    • The model effectively handles temporal segregation of complex image patterns.