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 global learning algorithm for a RBF network.

Qiuming Zhu1, Yao Cai, Luzheng Liu

  • 1Digital Imaging and Computer Vision Laboratory, University of Nebraska at Omaha, Omaha, USA

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

Genome-wide identification of the MAPK gene family in peanut (Arachis hypogaea L.) and functional characterization of AhMPK3 and AhMPK18 in plant innate immunity.

BMC plant biology·2026
Same author

Phase-based optoretinographic measurements of cones with a raster-scanning adaptive optics OCT are highly repeatable.

Biomedical optics express·2026
Same author

Dark adaptation of cone photoreceptor responses is revealed by optoretinography.

bioRxiv : the preprint server for biology·2026
Same author

A load forecasting method based on edge graph attention network.

PloS one·2026
Same author

Integrated pressure and torsion sensor with porous graphene aerogel electrodes embedded by conductive CuCo-MOFs.

Journal of colloid and interface science·2026
Same author

Sub-6 GHz acoustic filters using laterally-excited bulk acoustic resonator with scattering vias in double-layer electrodes.

Microsystems & nanoengineering·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

FedCAD: Cross-modal semantic alignment and distillation for cross-domain heterogeneous federated learning.

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

Partial-encryption-decryption-based secure state estimation of singularly perturbed complex networks: A Paillier encryption approach.

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

ResVaRe: Parameter-efficient fine-tuning for large language models via cross-layer residual vector adaptation and representation editing.

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

Brain network construction and analysis for epilepsy: A methodology review.

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

This study introduces a novel learning algorithm for Radial Basis Function (RBF) neural networks, enhancing both structure discovery and parameter training through a global maximum likelihood approach for improved pattern recognition.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Neural Networks

Background:

  • Radial Basis Function (RBF) neural networks are powerful tools for pattern recognition.
  • Existing methods often require separate processes for network structure determination and weight training.
  • A unified approach can lead to more efficient and effective network development.

Purpose of the Study:

  • To present a new, integrated learning algorithm for RBF neural network construction and training.
  • To leverage a global parameter learning mechanism based on maximum likelihood classification.
  • To enable the network to discover its structure and determine connection weights simultaneously.

Main Methods:

  • The algorithm employs a global parameter learning mechanism.

Related Experiment Videos

  • It utilizes a maximum likelihood classification approach.
  • The process gradually evolves the network structure and parameters.

    • Main Results:

    • The RBF network neurons partition the pattern space into maximum-size hyper-ellipsoid subspaces.
    • These subspaces are defined by the statistical distributions of training samples.
    • The learning process effectively integrates structure discovery and weight determination.

    Conclusions:

    • The proposed algorithm offers a unified approach to RBF neural network learning.
    • It efficiently determines both network architecture and connection weights.
    • This method facilitates the gradual evolution of the network and its parameters for optimal performance.