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

Robust radial basis function neural networks.

C C Lee1, P C Chung, J R Tsai

  • 1Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|February 7, 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

Comparing thallium-201 spect mammoscintigraphy and ultrasonography to detect breast cancer in mammographical dense breasts.

Neoplasma·2003
Same author

Detecting abnormal regional cerebral blood flow in patients with primary Sjögren's syndrome by technetium-99m ethyl cysteinate dimer single photon emission computed tomography of the brain--a preliminary report.

Rheumatology international·2003
Same author

Usefulness of quantitative Tc-99m HMPAO and Ga-67 citrate lung scans in detecting pulmonary vascular endothelium damage and lung inflammation in patients with systemic lupus erythematosus: a preliminary report.

Rheumatology international·2003
Same author

Treatment of toxic epidermal necrolysis in AIDS with intravenous immunoglobulins.

Clinical and experimental dermatology·2003
Same author

Usefulness of technetium-99m methoxyisobutylisonitrile liver single photon emission computed tomography to detect hepatocellular carcinoma.

Neoplasma·2003
Same author

Effect of rice--glycerol complex medium on the production of Lovastatin by Monascus ruber.

Folia microbiologica·2003
Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015
Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
See all related articles

This study introduces a novel radial basis function (RBF) network using sigmoidal functions and a robust objective function. The enhanced RBF network improves function approximation accuracy and robustness to outliers, outperforming traditional Gaussian-based RBF networks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Radial basis function (RBF) networks are effective for function approximation due to their rapid learning capabilities.
  • Traditional RBF networks using Gaussian functions struggle with approximating constant values and are sensitive to outliers, leading to inaccurate interpolations.

Purpose of the Study:

  • To address limitations of traditional RBF networks, this paper proposes a novel RBF network architecture.
  • The goal is to enhance approximation accuracy for constant-valued functions and improve robustness against large errors and outliers.

Main Methods:

  • The proposed RBF network utilizes sequences of sigmoidal functions as basis functions, replacing traditional Gaussian functions.
  • A robust objective function is incorporated to mitigate the impact of significant errors during training.

Related Experiment Videos

Main Results:

  • The novel RBF network demonstrates superior capability in approximating underlying functions compared to conventional RBF networks.
  • The proposed network exhibits faster learning speeds, requires a smaller network size, and shows high robustness to outliers.

Conclusions:

  • The sigmoidal function-based RBF network offers significant advantages over traditional Gaussian-based RBF networks.
  • This approach provides more accurate function approximation, faster learning, reduced network complexity, and enhanced robustness, making it suitable for diverse applications.