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

Chaotifying linear Elman networks.

Xiang Li1, Guanrong Chen, Zengqiang Chen

  • 1Dept. of Autom., Nankai Univ., Tianjin, China.

IEEE Transactions on Neural Networks
|February 5, 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

Laplacian spectrum constrains collective performance enhancement.

Physical review. E·2026
Same author

Coexistence of many positive invariant sets in several classes of dynamical systems.

Chaos (Woodbury, N.Y.)·2026
Same author

Fuzzy reinforcement learning synchronization of stochastic dynamic networks: An adaptive event-triggered strategy.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Bipartite Containment of Second-Order Multiagent Systems With Compound Noise Under Fixed or Markovian Switching Signed Topology.

IEEE transactions on cybernetics·2026
Same author

Community structure unveils the path multiplicity in complex networks.

Nature communications·2026
Same author

Symmetry prior based reconstruction of higher-order networks from time-series data.

Chaos (Woodbury, N.Y.)·2026
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

Researchers designed Elman networks, a type of recurrent neural network, to purposefully generate chaos. By incorporating a nonlinear modulo operation, these networks can achieve mathematical chaos, verified through simulations.

Area of Science:

  • Computational Neuroscience
  • Chaos Theory
  • Artificial Neural Networks

Background:

  • Recurrent neural networks (RNNs), specifically Elman networks, are explored for their potential beyond standard pattern recognition.
  • The integration of nonlinear dynamics into artificial neural networks offers novel computational capabilities.

Purpose of the Study:

  • To develop a method for purposefully generating chaos using Elman networks.
  • To establish conditions for Elman networks to produce chaos conforming to the Li-Yorke definition.
  • To design and validate specific weight matrices for achieving Li-Yorke chaos in Elman networks.

Main Methods:

  • A linear model of Elman networks was combined with a nonlinear modulo (mod) operation on the activation function.
  • Mathematical conditions on the weight matrix were derived to ensure the generated chaos meets the Li-Yorke criteria.

Related Experiment Videos

  • Representative weight matrices were constructed and implemented in Elman network designs.

    • Main Results:

    • The study successfully derived conditions for Elman networks to generate chaos.
    • Designed Elman networks demonstrated the ability to produce chaos satisfying the Li-Yorke definition.
    • Numerical simulations confirmed the effectiveness of the designed networks in generating and visualizing chaos.

    Conclusions:

    • The integration of a nonlinear modulo operation into Elman networks provides a viable method for generating mathematical chaos.
    • The derived weight matrix conditions enable the design of Elman networks capable of producing Li-Yorke chaos.
    • This research opens avenues for exploring chaotic dynamics within artificial neural network architectures for potential applications.