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

Training winner-take-all simultaneous recurrent neural networks.

Xindi Cai1, Danil V Prokhorov, Donald C Wunsch

  • 1Manuscript received September 26, 2005; revised June 25, 2006 and American Power Conversion Corporation, O'Fallon, MO 63368, USA xindi.cai@apc.com

IEEE Transactions on Neural Networks
|May 29, 2007
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

Current state of the art of new prostate MRI technologies and potential future developments.

BJR open·2026
Same author

Prostate Cancer: Current Status of Novel Molecular Imaging and Future Prospects.

European urology focus·2025
Same author

DeepART: Deep gradient-free local learning with adaptive resonance.

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

Adaptive Nussbaum Design for Nonholonomic Systems With Asymptotic Stabilization Against False Data Injection.

IEEE transactions on cybernetics·2025
Same author

The visualization of Orphadata neurology phenotypes.

Frontiers in digital health·2023
Same author

Subtypes of relapsing-remitting multiple sclerosis identified by network analysis.

Frontiers in digital health·2023
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

This study explores simultaneous recurrent networks (SRNs) trained with Kalman filters to find the maximum value among N numbers. The method effectively identifies the maximum and performs classification tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Winner-take-all (WTA) networks are crucial for database management, VLSI design, and digital processing.
  • The synthesis of WTA networks on single-layer, fully connected architectures with sigmoid transfer functions requires further investigation.

Purpose of the Study:

  • To explore the synthesis of WTA networks using simultaneous recurrent networks (SRNs).
  • To apply SRNs trained by Kalman filter algorithms for identifying the maximum among N numbers.
  • To evaluate the effectiveness of this training approach in classification tasks.

Main Methods:

  • Utilizing simultaneous recurrent networks (SRNs) for WTA network synthesis.
  • Employing Kalman filter algorithms for training SRNs.

Related Experiment Videos

  • Testing the approach on finding the maximum of N numbers and a car engine dataset classification.

    • Main Results:

    • Simulations confirmed the effectiveness of the Kalman filter training approach for SRNs.
    • A shared-weight SRN architecture successfully identified the maximum value.
    • A more general SRN demonstrated success in a real-world car engine data classification application.

    Conclusions:

    • Kalman filter-trained SRNs provide an effective method for WTA network synthesis.
    • The proposed method is applicable to both numerical maximum finding and classification tasks.
    • This research contributes to the understanding and application of SRNs in digital processing and machine learning.