Jove
Visualize
Contact Us

Related Experiment Videos

A dynamical adaptive resonance architecture.

G L Heileman1, M Georgiopoulos, C Abdallah

  • 1Dept. of Electr. and Comput. Eng., New Mexico Univ., Albuquerque, NM.

IEEE Transactions on Neural Networks
|January 1, 1994
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

Surgical practice variation and outcomes regarding single-level posterior approach for degenerative lumbar spondylolisthesis: a Canadian Spine Outcomes Research Network (CSORN) study.

The spine journal : official journal of the North American Spine Society·2025
Same author

Learn how to interpret and use intracranial EEG findings.

Epileptic disorders : international epilepsy journal with videotape·2023
Same author

Targeted density electrode placement achieves high concordance with traditional high-density EEG for electrical source imaging in epilepsy.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2023
Same author

Retained surfactant catheter and pneumothorax in a premature neonate.

Journal of neonatal-perinatal medicine·2016
Same author

Premedication of the child undergoing surgery.

Middle East journal of anaesthesiology·2012
Same author

An adaptive multiobjective approach to evolving ART architectures.

IEEE transactions on neural networks·2010
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 presents nonlinear differential equations for the Adaptive Resonance Theory 1 (ART1) model, enabling its realization as a self-contained dynamical system. Simulations confirm its effective learning behavior.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Dynamical Systems Theory

Background:

  • The Adaptive Resonance Theory 1 (ART1) model is a foundational neural network architecture for unsupervised learning and pattern recognition.
  • Existing ART1 models often rely on external control mechanisms, limiting their intrinsic dynamical properties.
  • Extensions by Carpenter and Grossberg (1987) provided a basis for exploring ART1's dynamics.

Purpose of the Study:

  • To formulate a set of nonlinear differential equations that intrinsically describe the ART1 model's dynamics.
  • To demonstrate how these equations allow the ART1 model to function as a collective nonlinear dynamical system.
  • To analytically and numerically validate the model's behavior in both fast and slow learning scenarios.

Main Methods:

Related Experiment Videos

  • Development of coupled nonlinear differential equations extending previous ART1 formulations.
  • Realization of the ART1 model as a collective nonlinear dynamical system without external control.
  • Analytical investigation of parameter selection for guaranteed ART1-equivalent behavior.
  • Numerical approximation techniques to simulate node and weight activity trajectories.

Main Results:

  • A complete dynamical system description of the ART1 model is established through nonlinear differential equations.
  • The proposed model operates autonomously, with dynamics fully determined by its internal equations.
  • Analytical methods confirm parameter settings for achieving fast and slow learning behaviors consistent with ART1.
  • Simulations successfully illustrate the temporal evolution of the network's activities.

Conclusions:

  • The presented nonlinear differential equations provide a robust, intrinsic dynamical framework for the ART1 model.
  • This formulation simplifies the ART1 model by eliminating the need for external control features.
  • The study validates the efficacy of the dynamical system approach for understanding and implementing ART1.