Jove
Visualize
Contact Us

Related Experiment Videos

Uniform Approximation and Gamma Networks.

Lilian Xu1, Irwin W. Sandberg

  • 1The University of Texas at Austin, USA

Neural Networks : the Official Journal of the International Neural Network Society
|July 1, 1997
PubMed
Summary

Researchers demonstrate that focused gamma networks can accurately approximate nonlinear input-output maps. This finding is significant for understanding and modeling complex systems in various scientific fields.

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

Surfactant protein-B polymorphisms and mortality in the acute respiratory distress syndrome.

Critical care medicine·2008
Same author

Genetic polymorphism in p53 codon 72 and skin cancer in southwestern Taiwan.

Journal of environmental science and health. Part A, Toxic/hazardous substances & environmental engineering·2003
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

Area of Science:

  • * System identification and nonlinear dynamics.
  • * Approximation theory in functional analysis.

Background:

  • * Nonlinear input-output maps are fundamental to modeling complex systems.
  • * Previous methods for approximating these maps had limitations.

Purpose of the Study:

  • * To investigate the approximation capabilities of focused gamma networks.
  • * To demonstrate uniform approximation for a specific class of nonlinear maps.

Main Methods:

  • * Analysis of single-variable, shift-invariant, causal, uniformly-fading-memory maps.
  • * Construction and theoretical validation of focused gamma networks.

Main Results:

  • * Proof that focused gamma networks can uniformly approximate any such map.
  • * Demonstration of arbitrary approximation accuracy.

Conclusions:

  • * Focused gamma networks offer a powerful tool for approximating nonlinear input-output systems.
  • * This work advances the theoretical understanding of nonlinear system modeling.

Related Experiment Videos