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 general mean-based iterative winner-take-all neural network.

J F Yang1, C M Chen, W C Wang

  • 1Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan.

IEEE Transactions on Neural Networks
|January 1, 1995
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

Developmental Changes in Pharyngeal Airway in the Male Population From Adolescence to Adulthood.

European journal of paediatric dentistry·2024
Same author

X-linked adrenoleukodystrophy in a child.

QJM : monthly journal of the Association of Physicians·2024
Same author

[Cytopathological features of hyalinizing trabecular tumor of the thyroid].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2022
Same author

[Construction of prediction model combined dual-energy CT quantitative parameters and conventional CT features for assessing the Ki-67 expression levels in invasive breast cancer].

Zhonghua yi xue za zhi·2022
Same author

Efficient solid-state Raman yellow laser at 579.5  nm.

Optics letters·2020
Same author

Roles of nurses and National Nurses Associations in combating COVID-19: Taiwan experience.

International nursing review·2020
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A new iterative winner-take-all (WTA) neural network offers faster convergence and better fault tolerance. This novel neural network requires fewer than Log(2)M iterations, making it suitable for diverse applications.

Area of Science:

  • Computational Neuroscience
  • Artificial Neural Networks
  • Machine Learning

Background:

  • Iterative winner-take-all (WTA) neural networks are crucial for competitive learning and pattern recognition.
  • Existing WTA networks face limitations in convergence speed and robustness.

Purpose of the Study:

  • To develop and analyze a novel one-layer iterative WTA neural network.
  • To evaluate the convergence behavior and fault tolerance of the proposed WTA network.

Main Methods:

  • Theoretical analysis of convergence properties.
  • Monte Carlo simulations for performance evaluation.
  • Analysis of fault tolerance through simulations.

Main Results:

Related Experiment Videos

  • The proposed WTA neural network demonstrates faster convergence, averaging fewer than Log(2)M iterations.
  • The network exhibits robust performance across three typical initial activation distributions.
  • Simulations confirm enhanced fault tolerance compared to existing iterative WTA nets.

    • Conclusions:

    • The novel iterative WTA neural network provides significant improvements in convergence speed.
    • The proposed network shows high robustness to errors, making it suitable for practical applications.
    • This WTA network is a promising candidate for various computational tasks requiring efficient and reliable winner-take-all processing.