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 Video

Updated: Jul 11, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

GFAM: evolving Fuzzy ARTMAP neural networks.

Ahmad Al-Daraiseh1, Assem Kaylani, Michael Georgiopoulos

  • 1School of EECS, University of Central Florida, Orlando, FL 32816-2786, United States. creepymaster@yahoo.com

Neural Networks : the Official Journal of the International Neural Network Society
|September 14, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Mesenteric vein thrombosis: a case series and current literature review.

International angiology : a journal of the International Union of Angiology·2025
Same author

Inflammation biomarkers as predictors of nodal metastases in colorectal cancer.

Folia medica·2025
Same author

Diagnostic accuracy of CRP in the drainage fluid for early detection of anastomotic leakage in colorectal surgery - a pilot study.

Folia medica·2025
Same author

Agnostic Biomarkers and Molecular Signatures in Colorectal Cancer-Guiding Chemotherapy and Predicting Response.

Biomedicines·2025
Same author

Dosimetric comparison of Acuros<sup>TM</sup> BV and AAPM TG-43 formalism for interstitial iridium-192 high-dose-rate brachytherapy.

Journal of contemporary brachytherapy·2024
Same author

Efficacy and safety of robotic complete mesocolic excision: a systematic review.

International journal of colorectal disease·2023

This study introduces GFAM, a novel Fuzzy ARTMAP neural network classifier that enhances generalization and reduces category proliferation. GFAM achieves optimal classification accuracy with minimal computational resources.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Fuzzy ARTMAP (ART) neural networks face challenges with generalization and category proliferation.
  • Existing ART classifiers struggle to balance accuracy with the number of created categories.

Purpose of the Study:

  • To evolve Fuzzy ARTMAP classifiers using genetic algorithms to improve generalization performance.
  • To address and alleviate the category proliferation problem in ART networks.
  • To introduce and evaluate the novel GFAM architecture.

Main Methods:

  • Genetic algorithms were employed to evolve Fuzzy ARTMAP classifiers.
  • Extensive experimentation was conducted on various classification problems.
  • The performance of the GFAM architecture was compared against other ARTMAP classifiers.

Related Experiment Videos

Last Updated: Jul 11, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Main Results:

  • The GFAM architecture demonstrated good generalization performance on unseen data.
  • GFAM effectively minimized category proliferation, creating fewer categories than necessary.
  • GFAM achieved optimal classification accuracy in several test cases with reasonable computational effort.
  • GFAM outperformed other competitive ARTMAP classifiers in the literature.

Conclusions:

  • GFAM represents a significant advancement in Fuzzy ARTMAP classifier evolution.
  • The proposed GFAM architecture offers a superior balance between classification accuracy and model complexity.
  • GFAM provides an effective solution for improving generalization and mitigating category proliferation in ART networks.