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 supervised learning network based on adaptive resonance theory

J Zhou1, S Bennett

  • 1Department of Automatic Control and Systems Engineering, University of Sheffield, UK. Zhou@acse.sheffield.ac.uk

International Journal of Neural Systems
|April 1, 1997
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

Calmodulin mediates calcium-dependent activation of the intermediate conductance KCa channel, IKCa1.

The Journal of biological chemistry·1999
Same author

Level of retinoblastoma protein expression correlates with p16 (MTS-1/INK4A/CDKN2) status in bladder cancer.

Oncogene·1999
Same author

Concept design of computer-aided study on traditional Chinese drugs.

Journal of chemical information and computer sciences·1999
Same author

Late onset of renal and hepatic cysts in Pkd1-targeted heterozygotes.

Nature genetics·1999
Same author

delta-catenin, an adhesive junction-associated protein which promotes cell scattering.

The Journal of cell biology·1999
Same author

Numeric modeling of the cardiovascular system with a left ventricular assist device.

ASAIO journal (American Society for Artificial Internal Organs : 1992)·1999
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

A novel neural network, fuzzy ART with logistic discrimination (ART-LD), enhances supervised learning for pattern recognition. This method effectively clusters data and generalizes predictions, demonstrating strong capabilities in classification tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Pattern recognition is crucial for data analysis and decision-making.
  • Supervised learning methods require efficient algorithms for accurate predictions.
  • Existing neural network architectures may face challenges in complex classification tasks.

Purpose of the Study:

  • To introduce a novel neural network architecture, fuzzy ART with logistic discrimination (ART-LD).
  • To demonstrate ART-LD's capability in supervised pattern recognition.
  • To evaluate the generalization performance of ART-LD on diverse datasets.

Main Methods:

  • ART-LD combines fuzzy ART for self-organized clustering with logistic discrimination for prediction.
  • The fuzzy ART module utilizes fuzzy set theory and competitive learning for stable category formation.

Related Experiment Videos

  • The logistic discrimination module generalizes fuzzy memberships to provide final predictions.

    • Main Results:

    • ART-LD successfully self-organizes input patterns into meaningful clusters.
    • The system demonstrates effective generalization capabilities in classification.
    • Performance was validated through simulated and real-world classification problems.

    Conclusions:

    • ART-LD offers a robust and efficient approach to supervised pattern recognition.
    • The hierarchical structure of ART-LD enhances both data clustering and predictive accuracy.
    • This architecture shows promise for various classification applications.