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 neural network classifier with disjunctive fuzzy information.

Hahn Ming Lee1, Kuo Hsiu Chen, I Feng Jiang

  • 1Department of Electronic Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

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 journal

DSN : Energy-efficient EMG signal classification method enabling real-time monitoring for edge healthcare.

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

An efficient stacked recurrent broad learning scheme for PV cluster power forecasting.

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

Robust and interpretable tabular data classification via multi-channel image conversion and channel-wise gating.

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

AdapHBNA: Adaptive hierarchical spatio-temporal brain network analysis for brain disease detection.

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

A practical design of backdoor trigger under frequency-based orthogonality constraints.

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

EEG fine-grained visual semantic decoding via a multimodal framework.

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

This study introduces a neural network that efficiently learns fuzzy patterns using prototype and exemplar nodes. This approach optimizes classification by adapting to data distribution and handling exceptions, reducing computational load.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Fuzzy Logic

Background:

  • Fuzzy information learning in feature spaces presents challenges for traditional neural networks.
  • Handling complex data distributions and exceptions requires adaptive classification models.

Purpose of the Study:

  • To present a novel neural network classifier capable of learning disjunctive fuzzy information.
  • To improve the efficiency and reduce the computational load of non-linear classification tasks.

Main Methods:

  • The proposed neural network utilizes two hidden layer node types: prototype nodes for cluster centroids and exemplar nodes for exceptions.
  • Prototypes are automatically generated and refined to create near-optimal decision regions.
  • Exemplars are employed to learn patterns not classified by prototypes, enabling efficient non-linear classification.

Related Experiment Videos

  • The model incorporates on-line learning capabilities.

    • Main Results:

    • The classifier effectively learns disjunctive fuzzy information in the feature space.
    • The adaptive generation of prototypes leads to near-optimal decision regions.
    • The strategy of using prototypes and exemplars reduces memory requirements and accelerates non-linear classification.
    • Experimental results demonstrate a reduction in hidden nodes through optimized prototype determination.

    Conclusions:

    • The developed neural network classifier offers an efficient method for learning complex fuzzy data.
    • The hybrid approach of prototype and exemplar nodes enhances classification accuracy and computational efficiency.
    • This model provides a promising solution for tasks requiring adaptive and robust fuzzy pattern recognition.