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 class of competitive learning models which avoids neuron underutilization problem.

C S Choy1, W C Siu

  • 1Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong.

IEEE Transactions on Neural Networks
|February 8, 2008
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

Immunohistochemical expression of NANOG in urothelial carcinoma of the bladder.

The Malaysian journal of pathology·2017
Same author

A deblocking technique for block-transform compressed image using wavelet transform modulus maxima.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

An efficient search strategy for block motion estimation using image features.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Adding learning to cellular genetic algorithms for training recurrent neural networks.

IEEE transactions on neural networks·2008
Same author

BiVisu: software tool for bicluster detection and visualization.

Bioinformatics (Oxford, England)·2007
Same author

A technique for extracting physiological parameters and the required input function simultaneously from PET image measurements: theory and simulation study.

IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society·2000
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

Multiplicatively biased competitive learning (MBCL) models prevent neuron underutilization. This competitive learning approach offers low computational complexity and optimal performance in various applications.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Competitive learning (CL) models are widely used in machine learning.
  • Neuron underutilization is a critical issue that can hinder optimal performance in CL models.
  • Existing CL models often suffer from high computational complexity or neuron underutilization.

Purpose of the Study:

  • To analyze the qualitative property of avoiding neuron underutilization in multiplicatively biased competitive learning (MBCL) models.
  • To investigate the potential of MBCL models for achieving optimal performance in various applications.
  • To highlight the practical advantages of MBCL models, including low computational complexity.

Main Methods:

  • Theoretical analysis of a class of competitive learning models.

Related Experiment Videos

  • Introduction of the multiplicatively biased competitive learning (MBCL) model.
  • Mathematical proof demonstrating that MBCL models avoid neuron underutilization with probability one as time approaches infinity.

    • Main Results:

    • MBCL models are proven to avoid neuron underutilization with probability one.
    • MBCL models exhibit low computational complexity compared to other CL models.
    • The findings suggest MBCL instances can achieve optimal performance in classification, vector quantization, and density estimation.

    Conclusions:

    • MBCL models offer a robust solution to the neuron underutilization problem in competitive learning.
    • The efficiency and effectiveness of MBCL models make them suitable for practical applications.
    • Further research can explore specific MBCL instances for enhanced performance in diverse machine learning tasks.