Jove
Visualize
Contact Us

Related Experiment Videos

Median radial basis function neural network.

A G Bors1, I Pitas

  • 1Dept. of Inf., Thessaloniki Univ.

IEEE Transactions on Neural Networks
|January 1, 1996
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

Introduction.

Optics express·2009
Same author

Image watermarking using block site selection and DCT domain constraints.

Optics express·2009
Same author

Optical flow estimation and moving object segmentation based on median radial basis function network.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Morphological iterative closest point algorithm.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Object classification in 3-D images using alpha-trimmed mean radial basis function network.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Fuzzy scalar and vector median filters based on fuzzy distances.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
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
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

This study introduces the median radial basis function (MRBF) algorithm for neural networks, offering a robust estimation method for improved pattern classification and optical flow segmentation.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Radial basis functions (RBFs) are two-layer neural networks where hidden units use kernel functions.
  • Kernel parameters are typically estimated using classical statistical methods, such as learning vector quantization.
  • Robust estimation techniques can offer improved performance in parameter estimation.

Purpose of the Study:

  • To introduce a novel robust estimation algorithm for radial basis function (RBF) networks.
  • To compare the performance of the proposed algorithm against classical estimation methods.
  • To evaluate the effectiveness of RBF networks trained with these methods in pattern classification and optical flow segmentation.

Main Methods:

  • The study proposes the median radial basis function (MRBF) algorithm, utilizing robust estimation for hidden unit parameters.

Related Experiment Videos

  • Kernel location is estimated using the marginal median, and scale parameters use the median of absolute deviations.
  • A histogram-based fast implementation for the MRBF algorithm is presented.
  • Theoretical performance is evaluated by comparing weight estimation accuracy against a classical approach based on learning vector quantization.

    • Main Results:

    • The MRBF algorithm demonstrates robust parameter estimation for RBF networks.
    • Comparative analysis shows the theoretical performance of MRBF against classical estimation methods.
    • The trained RBF networks are successfully applied to pattern classification and optical flow segmentation tasks.

    Conclusions:

    • The median radial basis function (MRBF) algorithm provides a robust alternative for training RBF networks.
    • Robust estimation techniques enhance the reliability of RBF network parameter estimation.
    • The MRBF algorithm shows promise for applications in pattern classification and optical flow segmentation.