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

Generalization, discrimination, and multiple categorization using adaptive resonance theory.

P Lavoie1, J F Crespo, Y Savaria

  • 1Defense Research Establishment-Ottawa, Ottawa, Ont., K1A 0Z4, Canada.

IEEE Transactions on Neural Networks
|February 7, 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

Aspergillus fumigatus Serum IgG Cut-Off for the Diagnosis of Aspergillus-Associated Lung Disease: A Historic Cohort Analysis.

Clinical and experimental allergy : journal of the British Society for Allergy and Clinical Immunology·2025
Same author

Successful Subcutaneous Desensitization to Certolizumab Pegol.

Journal of investigational allergology & clinical immunology·2024
Same author

Sunflower (Helianthus annuus) Seed Allergy.

Journal of investigational allergology & clinical immunology·2023
Same author

Stent-Assisted Coiling in the Treatment of Unruptured Intracranial Aneurysms: A Randomized Clinical Trial.

AJNR. American journal of neuroradiology·2023
Same author

THE ROLE OF METAL-ION BINDING IN MODIFYING THE TOXIC EFFECTS OF SULPHUR DIOXIDE ON THE LICHEN UMBILICARIA MUHLENBERGII: II. <sup>14</sup> C-FIXATION STUDIES.

The New phytologist·2022
Same author

THE ROLE OF METAL-ION BINDING IN MODIFYING THE TOXIC EFFECTS OF SULPHUR DIOXIDE ON THE LICHEN UMBILICARIA MUHLENBERGII: I. POTASSIUM EFFLUX STUDIES.

The New phytologist·2022
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 an attentional tuning parameter to Adaptive Resonance Theory (ART) neural networks, enabling flexible data categorization. This allows a single network to learn both general and specific patterns simultaneously.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Adaptive Resonance Theory (ART) models face challenges in balancing generalization and discrimination.
  • Internal competition between categories can lead to biased learning in ART networks.

Purpose of the Study:

  • To introduce an external control mechanism to bias category competition in ART networks.
  • To enable a single ART network to learn and recall categories with varying degrees of generality.

Main Methods:

  • Modified the ART choice function to include an externally controlled attentional tuning parameter.
  • Linked the attentional tuning parameter with the ART vigilance parameter in a simplified model.
  • Analyzed network behavior with varying attentional tuning and vigilance levels.

Related Experiment Videos

Main Results:

  • The modified ART network can learn and recall different categories (general and specific) for the same input by adjusting the attentional tuning parameter.
  • Multiple levels of categorization coexist within a single ART network.
  • The self-stabilization property is maintained for arbitrary input sequences and vigilance level orderings.

Conclusions:

  • External control via an attentional tuning parameter enhances the flexibility of ART neural networks.
  • This approach allows for simultaneous general and specific data categorization within one model.
  • The modified ART model retains its self-stabilization properties, ensuring robust learning.