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

Selecting radial basis function network centers with recursive orthogonal least squares training.

J B Gomm1, D L Yu

  • 1Control Systems Research Group, School of Engineering, Liverpool John Moores University, Liverpool L3 3AF, UK.

IEEE Transactions on Neural Networks
|February 6, 2008
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

[Whole-course management strategies for gastroesophageal reflux disease: an evidence mapping study based on clinical practice guidelines].

Zhonghua wei chang wai ke za zhi = Chinese journal of gastrointestinal surgery·2023
Same author

Visible imaging system with changeable field of view on the HL-2A tokamak.

The Review of scientific instruments·2022
Same author

[Clinical analysis of pulmonary sequestration with torsion in 4 cases and literature review].

Zhonghua jie he he hu xi za zhi = Zhonghua jiehe he huxi zazhi = Chinese journal of tuberculosis and respiratory diseases·2021
Same author

Visible wide-angle view imaging system for the first plasma on the HL-2M tokamak.

Applied optics·2021
Same author

Fast charge exchange recombination spectroscopy on HuanLiu-2A tokamak.

The Review of scientific instruments·2020
Same author

[One case report of tonsil metastatic cutaneous achromatic melanoma].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2019
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Recursive orthogonal least squares (ROLS) efficiently selects centers for radial basis function (RBF) networks. This method reduces network size without retraining, achieving accurate models for complex processes.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Science

Background:

  • Radial basis function (RBF) networks are powerful tools for modeling complex systems.
  • Traditional RBF network training can be computationally intensive and memory-demanding.
  • Recursive orthogonal least squares (ROLS) offers a robust and memory-efficient alternative for weight determination.

Purpose of the Study:

  • To extend the application of ROLS for selecting centers in RBF networks.
  • To develop efficient methods for RBF network reduction without compromising accuracy.
  • To demonstrate the utility of ROLS-based center selection in practical applications.

Main Methods:

  • Utilizing information from the ROLS algorithm post-training for sequential center selection.

Related Experiment Videos

  • Developing two distinct center selection strategies: forward and backward methods.
  • Applying the developed methods to model a nonlinear time series and a multi-input-multi-output chemical process.

    • Main Results:

    • Demonstrated that ROLS can effectively identify optimal centers for RBF networks.
    • Achieved significant reductions in the number of network centers required.
    • Obtained accurate network models for both time series and chemical process applications.

    Conclusions:

    • ROLS-based center selection provides an efficient approach for RBF network architecture optimization.
    • Network reduction using ROLS is feasible without the need for complete retraining.
    • The proposed methods offer a practical solution for developing smaller, accurate RBF network models.