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

Neighborhood sequential and random training techniques for CMAC.

D E Thompson1, S Kwon

  • 1Dept. of Mech. Eng., New Mexico Univ., Albuquerque, NM.

IEEE Transactions on Neural Networks
|January 1, 1995
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

Black Hole Spectroscopy and Tests of General Relativity with GW250114.

Physical review letters·2026
Same author

GW250114: Testing Hawking's Area Law and the Kerr Nature of Black Holes.

Physical review letters·2025
Same author

Expert-involved continuous renal replacement therapy device development: addressing user needs through human factors engineering.

Expert review of medical devices·2025
Same author

Ventriculophasic response in a horse with atrioventricular block.

Journal of veterinary cardiology : the official journal of the European Society of Veterinary Cardiology·2025
Same author

How Neighborhood Structural and Individual Characteristics Affect Frailty Progression: Evidence from the China Health and Retirement Longitudinal Study.

The journal of nutrition, health & aging·2023
Same author

Feasibility Study for an Automated Engineering Change Process.

International journal of production research·2023
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

Two training methods for Cerebellar Model Articulation Controller (CMAC) adaptive control systems were compared. Neighborhood sequential training offers faster learning, while random training achieves higher precision for mathematical function generation.

Area of Science:

  • * Robotics and Control Systems
  • * Artificial Intelligence and Machine Learning

Background:

  • * Adaptive control algorithms are crucial for systems requiring real-time adjustments.
  • * Cerebellar Model Articulation Controller (CMAC) is a neural network model known for its adaptive capabilities and generalization properties.
  • * Training interference due to generalization can hinder CMAC system performance.

Purpose of the Study:

  • * To investigate and compare two novel training techniques for CMAC systems: neighborhood sequential training and random training.
  • * To evaluate the effectiveness of these methods in generating mathematical functions while mitigating training interference.
  • * To analyze the trade-offs between training speed, precision, and convergence for each method.

Main Methods:

  • * Development of a neighborhood sequential training strategy leveraging CMAC's address space for efficient point selection.

Related Experiment Videos

  • * Implementation of a random training method for CMAC system parameter optimization.
  • * Application of both training techniques to generate mathematical functions and assess performance.

    • Main Results:

    • * Both neighborhood sequential and random training successfully circumvented training interference inherent in CMAC.
    • * Neighborhood sequential training demonstrated faster convergence by strategically utilizing CMAC's discrete state space.
    • * Random training achieved higher precision in converging to the target training function, albeit with longer training durations.

    Conclusions:

    • * Both devised training methods are effective for CMAC systems, offering distinct advantages.
    • * Neighborhood sequential training provides rapid learning, suitable for time-sensitive applications.
    • * Random training offers superior precision, ideal for applications demanding high accuracy, despite longer training times.