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

Wavelet basis function neural networks for sequential learning.

Ning Jin1, Derong Liu

  • 1Department of Electrical and Computer Engineering, University of Illinois, Chicago, IL 60607-7053, USA. njin@ece.uic.edu

IEEE Transactions on Neural Networks
|March 13, 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

The OsCPK4-OsCNGC7 phosphorylation-centered feedback loop promotes Ca<sup>2+</sup> influx and confers salt tolerance in rice.

Plant communications·2026
Same author

Comparison of compressed sensing and conventional 4D flow MRI for turbulent kinetic energy assessment in healthy participants and patients with aortic stenosis.

Scientific reports·2026
Same author

Source apportionment of PM<sub>2.5</sub>-bound elemental carbon via stable carbon isotope analysis: A comparison study with receptor model.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

The in vivo inhibitory function of the MHC-I α3 domain-CD8α interaction.

bioRxiv : the preprint server for biology·2026
Same author

Feasibility of Magnetic Resonance Imaging-Guided Pulmonary Artery Stenting in a Commercial Wide-Bore 0.55-T Scanner.

JACC. Basic to translational science·2026
Same author

A retrospective analysis of the correlation between vaginal microecology and high-risk HPV infection among 5727 women.

BMC infectious diseases·2026
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

Wavelet basis function neural networks (WBFNNs) offer improved function approximation. WBFNNs demonstrate better generalization and faster training compared to radial basis function neural networks (RBFNNs).

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Radial Basis Function Neural Networks (RBFNNs) are widely used for function approximation.
  • Wavelet Neural Networks (WNNs) also utilize wavelet functions for approximation.
  • A need exists for neural network architectures with enhanced generalization and efficiency.

Purpose of the Study:

  • To introduce and develop Wavelet Basis Function Neural Networks (WBFNNs).
  • To investigate the function approximation capabilities of WBFNNs.
  • To compare the performance of WBFNNs against RBFNNs.

Main Methods:

  • Developed WBFNNs incorporating both scaling and wavelet functions from multiresolution approximation (MRA).
  • Implemented a sequential learning algorithm for WBFNN training.

Related Experiment Videos

  • Compared the sequential learning algorithm of WBFNNs with that of RBFNNs.

    • Main Results:

    • WBFNNs utilize both scaling and wavelet functions for function approximation.
    • Experimental results indicate superior generalization properties for WBFNNs.
    • WBFNNs achieved shorter training times compared to RBFNNs.

    Conclusions:

    • WBFNNs represent a novel neural network architecture with significant advantages.
    • The proposed WBFNNs outperform traditional RBFNNs in terms of generalization and training efficiency.
    • WBFNNs show promise for advanced function approximation tasks.