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

Universal learning network and its application to chaos control.

K Hirasawa1, X Wang, J Murata

  • 1Department of Electrical and Electronic Systems Engineering, Graduate School of Information Science and Electrical Engineering, Kyushu University, Japan. hirasawa@ees.kyushu-u.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|August 10, 2000
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

Evidence of Spin-Interference Effects in Exclusive J/ψ→e^{+}e^{-} Photoproduction in Ultraperipheral Heavy-Ion Collisions.

Physical review letters·2026
Same author

First Observation of Deuteron-Λ Correlations at RHIC.

Physical review letters·2026
Same author

Observation of Charmonium Sequential Suppression in Heavy-Ion Collisions at the Relativistic Heavy Ion Collider.

Physical review letters·2026
Same author

Energy Independence of the Collins Asymmetry in p^{↑}p Collisions.

Physical review letters·2026
Same author

Precision Measurement of Net-Proton-Number Fluctuations in Au+Au Collisions at RHIC.

Physical review letters·2025
Same author

Measurement of Two-Point Energy Correlators within Jets in p+p Collisions at sqrt[s]=200  GeV.

Physical review letters·2025

Universal Learning Networks (ULNs) offer a unified framework for modeling complex systems, extending beyond traditional neural networks. A novel learning algorithm optimizes ULNs for chaos control by adjusting parameters to target specific Lyapunov exponents.

Area of Science:

  • Complex Systems Modeling
  • Computational Neuroscience
  • Nonlinear Dynamics

Background:

  • Traditional neural networks and fuzzy neural networks have limitations in modeling complex systems with arbitrary time delays.
  • A generalized framework is needed to unify the modeling of physical systems and their controllers.

Purpose of the Study:

  • To introduce Universal Learning Networks (ULNs) as a generalized framework for modeling and controlling complex systems.
  • To develop a generalized learning algorithm for optimizing ULNs, incorporating higher-order derivatives.
  • To apply ULNs to chaos control using the maximum Lyapunov exponent.

Main Methods:

  • ULNs are defined with interconnected nodes, nonlinear functions, and multi-branch connections with arbitrary time delays.
  • A generalized learning algorithm is derived using forward or backward propagation for calculating first and higher-order derivatives.

Related Experiment Videos

  • Chaos control is achieved by formulating the maximum Lyapunov exponent of ULNs and adjusting parameters.

    • Main Results:

    • The generalized learning algorithm extends existing methods like BPTT and RTRL to handle complex ULN structures and higher-order derivatives.
    • A chaos control method using ULNs and their maximum Lyapunov exponent is proposed and validated.
    • Simulations demonstrate that a three-node fully connected ULN can exhibit chaotic behaviors.

    Conclusions:

    • ULNs provide a powerful and unified approach to modeling diverse complex systems, surpassing limitations of existing neural network models.
    • The developed generalized learning algorithm enables effective optimization of ULNs for advanced control applications, including chaos control.
    • ULNs represent a significant advancement in the field, with demonstrated potential for controlling chaotic dynamics.