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 MDL-based construction of RBF networks.

Ales Leonardis1, Horst Bischof

  • 1Faculty of Computer and Information Science, University of Ljubljana, SI-1001, Ljubljana, Slovenia

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
PubMed
Summary

This study introduces a novel method to optimize Radial Basis Function (RBF) networks by adaptively training and selecting basis functions. The approach balances network accuracy, training time, and complexity for improved performance.

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

Transformer-Based Models for Predicting Molecular Structures from Infrared Spectra Using Patch-Based Self-Attention.

The journal of physical chemistry. A·2025
Same author

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT.

Communications medicine·2025
Same author

Structure and Intensity Unbiased Translation for 2D Medical Image Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Image capturing, segmentation and data analysis of shredded refuse streams.

Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA·2024
Same author

Weakly-Supervised RGBD Video Object Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
Same author

FlexHDR: Modeling Alignment and Exposure Uncertainties for Flexible HDR Imaging.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Radial Basis Function (RBF) networks are powerful tools for function approximation and classification.
  • Optimizing RBF network complexity is crucial for efficient and accurate performance.
  • Existing methods may not adequately balance accuracy, training time, and network size.

Purpose of the Study:

  • To propose and evaluate a novel method for optimizing the complexity of Radial Basis Function (RBF) networks.
  • To introduce a two-procedure approach involving adaptive training and basis function selection.
  • To achieve a controlled balance between accuracy, training time, and network complexity.

Main Methods:

  • The proposed method combines adaptive training of basis function locations and widths with linear weight training.

Related Experiment Videos

  • A selection procedure eliminates redundant basis functions using an objective function based on the Minimum Description Length (MDL) principle.
  • Iterative combination of adaptation and selection procedures allows for controlled network modification.

    • Main Results:

    • The method successfully optimizes RBF network complexity for function approximation and classification tasks.
    • The proposed approach demonstrates a favorable balance between network accuracy, training efficiency, and reduced complexity.
    • Comparative analysis shows competitive or superior performance against other recently proposed RBF network optimization methods.

    Conclusions:

    • The presented method offers an effective strategy for optimizing Radial Basis Function (RBF) network complexity.
    • This approach provides a controlled mechanism to manage the trade-offs between accuracy, training time, and network size.
    • The findings suggest the utility of the MDL principle in guiding the selection of parsimonious RBF networks.