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

Distributed ARTMAP: a neural network for fast distributed supervised learning.

Gail A. Carpenter1, Boriana L. Milenova, Benjamin W. Noeske

  • 1Center for Adaptive Systems and Department of Cognitive and Neural Systems, Boston University, Boston, USA

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
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

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks.

Neural networks : the official journal of the International Neural Network Society·2003
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Distributed ARTMAP (dARTMAP) offers real-time supervised learning by combining multi-layer perceptrons (MLPs) and adaptive resonance theory (ART). This novel approach enhances memory compression and noise tolerance while maintaining accuracy.

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Artificial Intelligence

Background:

  • Multi-layer perceptrons (MLPs) offer memory compression and noise tolerance via distributed coding but require slow, offline learning to prevent catastrophic forgetting.
  • Adaptive Resonance Theory (ART) models ensure stable memories with fast online learning but often rely on winner-take-all coding, risking category proliferation in noisy environments.

Purpose of the Study:

  • To introduce a novel distributed ARTMAP (dARTMAP) system for real-time supervised learning.
  • To combine the computational strengths of MLPs and ART models in a unified neural network architecture.
  • To improve upon existing models by enhancing memory compression and contrast control.

Main Methods:

  • Development of an implementation algorithm for a class of dARTMAP networks.

Related Experiment Videos

  • Integration of unsupervised distributed ART (dART) model principles.
  • Inclusion of a novel content-addressable memory (CAM) rule for enhanced coding field contrast control.

    • Main Results:

    • The dARTMAP system demonstrates the ability to retain the accuracy of fuzzy ARTMAP.
    • Significant improvements in memory compression were observed compared to existing models.
    • The dARTMAP system reduces to fuzzy ARTMAP under winner-take-all coding conditions.

    Conclusions:

    • dARTMAP successfully merges MLP and ART advantages for efficient, real-time supervised learning.
    • The proposed CAM rule enhances network performance, particularly in contrast control.
    • dARTMAP offers a promising advancement in neural network design for supervised learning tasks requiring robust memory and compression.