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

Multiwavelet neural network and its approximation properties.

L Jiao1, J Pan, Y Fang

  • 1Key Laboratory for Radar Signal Processing, Xidian University, Xi'an 710071, China.

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

Measurement of ϒ(1S) Elliptic Flow at Forward Rapidity in Pb-Pb Collisions at sqrt[s_{NN}]=5.02  TeV.

Physical review letters·2019
Same author

[Artificial intelligence in lung imaging].

Der Radiologe·2019
Same author

Investigations of Anisotropic Flow Using Multiparticle Azimuthal Correlations in pp, p-Pb, Xe-Xe, and Pb-Pb Collisions at the LHC.

Physical review letters·2019
Same author

[The treatment effect of opening,debridement and double-row fixation using suture anchor for severe patellar tendinopathy].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2019
Same author

Influences of melatonin and endotoxin lipopolysaccharide on goose productive performance and gut microbiota.

British poultry science·2019
Same author

[Effect of triangular flap design and healing procedure on the sequelae after extraction of impacted lower third molars].

Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences·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

Multiwavelet neural networks offer faster convergence than traditional wavelet networks, especially for smooth functions. Experiments confirm this improved performance, though approximation is similar at jump discontinuities.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Signal Processing

Background:

  • Wavelet networks are effective function approximators.
  • Multiwavelets offer potential advantages over wavelets due to their properties.

Purpose of the Study:

  • To propose and analyze a novel multiwavelet-based neural network model.
  • To compare its approximation properties and convergence rates against traditional wavelet networks.

Main Methods:

  • Developed a multiwavelet neural network architecture.
  • Proved universal and L(2) approximation properties and consistency.
  • Estimated convergence rates.
  • Conducted comparative experiments using Lemarie-Meyer, Daubechies2, and GHM multiwavelet networks.

Related Experiment Videos

Main Results:

  • The multiwavelet network demonstrates superior convergence rates compared to wavelet networks for smooth functions.
  • Theoretical analysis is well-supported by experimental results.
  • Approximation performance is comparable between the two network types at jump discontinuities.

Conclusions:

  • Multiwavelet neural networks provide a more efficient alternative to wavelet networks for approximating smooth functions.
  • The proposed model offers enhanced convergence properties.
  • Further research may explore applications where rapid convergence is critical.