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

Improving ARTMAP learning through variable vigilance.

A Canuto1, M Fairhurst, G Howells

  • 1Electronic Engineering Laboratory, University of Kent, Canterbury, Kent CT27NT, UK. amdc1@ukc.ac.uk

International Journal of Neural Systems
|February 20, 2002
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

Disappointed Love and Suicide: A Randomized Controlled Trial of "Abandonment Psychotherapy" Among Borderline Patients.

Journal of personality disorders·2015
Same author

[Disease and the encounter with the incomprehensible].

Revue medicale suisse·2015
Same author

[Neurological diseases and suicide: from neurobiology to hopelessness].

Revue medicale suisse·2015
Same author

[Do not abandon Philoctetes].

Revue medicale suisse·2013
Same author

[Multidisciplinary care during peripartum: mother-baby dyad in the center of the relational constellations].

Revue medicale suisse·2013
Same author

[Prostate cancer and androgen deprivation: benefits of psychological counseling].

Revue medicale suisse·2013
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

This study introduces a variable vigilance mechanism for the RePART fuzzy neural network, reducing category proliferation in ARTMAP-based systems. This innovation enhances model performance and simplifies network structure.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • ARTMAP-based networks can suffer from category proliferation, leading to complex and inefficient models.
  • The vigilance parameter in fuzzy neural networks is crucial for category formation and network stability.

Purpose of the Study:

  • To propose and evaluate a novel mechanism for dynamically adjusting the vigilance parameter in the RePART fuzzy neural network.
  • To address the issue of category proliferation inherent in ARTMAP-based architectures.
  • To enhance the performance and structural efficiency of the RePART model.

Main Methods:

  • Implementation of a variable vigilance parameter within the RePART fuzzy neural network architecture.
  • Comparative analysis of the RePART model with the proposed mechanism against standard ARTMAP-based networks.

Related Experiment Videos

  • Empirical experimentation to assess performance metrics and structural complexity.

    • Main Results:

    • The variable vigilance mechanism effectively mitigates category proliferation in the RePART model.
    • Empirical experiments demonstrate improved performance of the RePART model with variable vigilance.
    • The proposed mechanism leads to a reduction in the structural complexity of the RePART network.

    Conclusions:

    • Dynamic adjustment of the vigilance parameter is a viable strategy for enhancing fuzzy neural network performance.
    • The RePART model with variable vigilance offers a more efficient and less complex alternative to traditional ARTMAP networks.
    • This research contributes to the development of more robust and scalable fuzzy neural network systems.