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

Competitive learning with generalized winner-take-all activation.

M Lemmon1, B V Kumar

  • 1Dept. of Electr. and Comput. Eng., Carnegie Mellon Univ., Pittsburg, PA.

IEEE Transactions on Neural Networks
|January 1, 1992
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

Winds at the Mars 2020 Landing Site. 2. Wind Variability and Turbulence.

Journal of geophysical research. Planets·2023
Same author

The sound of a Martian dust devil.

Nature communications·2022
Same author

Pre-Flight Calibration of the Mars 2020 Rover Mastcam Zoom (Mastcam-Z) Multispectral, Stereoscopic Imager.

Space science reviews·2021
Same author

The Mars 2020 <i>Perseverance</i> Rover Mast Camera Zoom (Mastcam-Z) Multispectral, Stereoscopic Imaging Investigation.

Space science reviews·2021
Same author

Effects of the MY34/2018 Global Dust Storm as Measured by MSL REMS in Gale Crater.

Journal of geophysical research. Planets·2019
Same author

Human immunology studies using organ donors: Impact of clinical variations on immune parameters in tissues and circulation.

American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons·2017
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 introduces a generalized winner-take-all (g-WTA) model for competitive learning. This mathematical framework helps design algorithms to estimate probability density functions by analyzing neural flux and weight vector density.

Area of Science:

  • Computational neuroscience
  • Machine learning theory

Background:

  • Competitive learning paradigms commonly use winner-take-all (WTA) activation rules.
  • Existing models may not capture the full dynamics of competitive learning processes.

Purpose of the Study:

  • To develop a generalized mathematical model for competitive learning paradigms.
  • To extend the standard winner-take-all (WTA) activation rule to a generalized version (g-WTA).
  • To provide a framework for designing novel competitive learning algorithms.

Main Methods:

  • Formulation of a partial differential equation (PDE) modeling competitive learning dynamics.
  • Relating the time rate of change in weight vector density to the divergence of the neural flux.
  • Utilizing characteristic trajectories to analyze solutions of the PDE model.

Related Experiment Videos

Main Results:

  • The developed PDE model provides a novel mathematical description of competitive learning.
  • Analysis of characteristic trajectories reveals insights into the behavior of weight vector density.
  • Demonstration of how the model facilitates the design of algorithms for estimating probability density functions.

Conclusions:

  • The generalized winner-take-all (g-WTA) model offers a powerful mathematical tool for competitive learning.
  • This approach enables the estimation of modes in unknown probability density functions.
  • The study advances the theoretical understanding and practical application of competitive learning algorithms.