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

Self-learning fuzzy controllers based on temporal backpropagation.

J R Jang1

  • 1Dept. of Electr. Eng. and Comput. Sci., California Univ., Berkeley, CA.

IEEE Transactions on Neural Networks
|January 1, 1992
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

Comments on "Functional equivalence between radial basis function networks and fuzzy inference systems".

IEEE transactions on neural networks·2008
Same author

Functional equivalence between radial basis function networks and fuzzy inference systems.

IEEE transactions on neural networks·1993
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

A novel temporal backpropagation method enhances fuzzy controllers with self-learning for optimal control. This approach refines or generates fuzzy rules, demonstrating effectiveness on an inverted pendulum system.

Area of Science:

  • Control Systems Engineering
  • Artificial Intelligence
  • Machine Learning

Background:

  • Fuzzy controllers offer intuitive rule-based systems but often lack adaptability.
  • Optimizing fuzzy controller performance typically requires expert knowledge or extensive tuning.
  • Self-learning capabilities are crucial for enhancing control system adaptability and performance.

Purpose of the Study:

  • To present a generalized control strategy that integrates self-learning into fuzzy controllers.
  • To introduce a novel methodology, temporal backpropagation, for enhancing fuzzy control.
  • To enable fuzzy controllers to achieve near-optimal control objectives autonomously.

Main Methods:

  • Developed a temporal backpropagation algorithm for fuzzy controller self-learning.

Related Experiment Videos

  • The method is model-sensitive, applicable to piecewise-differentiable plant models (e.g., difference equations, neural networks, fuzzy models).
  • The approach can refine existing expert-defined fuzzy rules or generate new rules automatically.

    • Main Results:

    • Demonstrated the effectiveness of the temporal backpropagation control scheme using the inverted pendulum system as a testbed.
    • Showcased the ability to refine expert fuzzy rules and automatically derive fuzzy rules when experts are unavailable.
    • Validated the robustness of the acquired fuzzy controller through experimental results.

    Conclusions:

    • The proposed temporal backpropagation strategy effectively enhances fuzzy controllers with self-learning capabilities.
    • This methodology provides a robust and adaptable approach for achieving near-optimal control across various plant models.
    • The technique successfully addresses limitations of traditional fuzzy controllers, offering automated rule generation and refinement.