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

An Efficient Method to Construct a Radial Basis Function Neural Network Classifier.

Sung Yang Bang1, Young Sup Hwang

  • 1Pohang University of Science and Technology, Pohang, Korea

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

Face membership authentication using SVM classification tree generated by membership-based LLE data partition.

IEEE transactions on neural networks·2005
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

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

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

This study presents an efficient method for constructing Radial Basis Function Neural Network (RBFN) classifiers using fast clustering and statistical weight computation. The novel approach achieves superior performance in handwritten digit recognition tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Radial Basis Function Neural Networks (RBFN) are powerful universal function approximators.
  • Constructing an effective RBFN for specific problems can be challenging and non-intuitive.

Purpose of the Study:

  • To introduce an efficient and effective method for constructing Radial Basis Function Neural Network (RBFN) classifiers.
  • To address the complexities in RBFN design and implementation.

Main Methods:

  • Determining middle layer neurons via a fast clustering algorithm.
  • Statistically computing optimal weights between the middle and output layers.
  • Applying the method to unconstrained handwritten digit recognition.

Related Experiment Videos

Main Results:

  • The proposed method constructs RBFN classifiers rapidly.
  • The developed RBFN classifier demonstrated superior performance compared to previous benchmarks.
  • Achieved high accuracy in unconstrained handwritten digit recognition.

Conclusions:

  • The presented method offers an efficient and effective approach to RBFN classifier construction.
  • The technique significantly improves performance in pattern recognition tasks like handwritten digit recognition.
  • This methodology provides a practical solution for building high-performing RBFN models.