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

CMAC-based adaptive critic self-learning control.

C S Lin1, H Kim

  • 1Dept. of Electr. and Comput. Eng., Missouri Univ., Columbia, MO.

IEEE Transactions on Neural Networks
|January 1, 1991
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

Development of advanced photon calibrator for Kamioka gravitational wave detector (KAGRA).

The Review of scientific instruments·2023
Same author

Scintillation light detection in the 6-m drift-length ProtoDUNE Dual Phase liquid argon TPC.

The European physical journal. C, Particles and fields·2022
Same author

[Effects of direct antiviral agent on the frequency of peripheral blood mononuclear cells and their activating factors sCD14s and CD163 in patients with chronic hepatitis C].

Zhonghua gan zang bing za zhi = Zhonghua ganzangbing zazhi = Chinese journal of hepatology·2021
Same author

Prospects for beyond the Standard Model physics searches at the Deep Underground Neutrino Experiment: DUNE Collaboration.

The European physical journal. C, Particles and fields·2021
Same author

Severe myocardial bridge presenting as paroxysmal atrioventricular block.

Journal of postgraduate medicine·2021
Same author

Isolated intracardiac recurrence of diffuse large B-cell lymphoma successfully treated with rituximab and bendamustine chemotherapy regimen.

Journal of postgraduate medicine·2020
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

This study integrates the cerebellar model articulation controller (CMAC) into self-learning control, reducing memory needs and enhancing learning speed for larger-scale problems.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Control Systems

Background:

  • Traditional self-learning control schemes require significant memory for each quantized state.
  • The cerebellar model articulation controller (CMAC) offers potential for more efficient information storage and retrieval.

Purpose of the Study:

  • To integrate CMAC into a self-learning control scheme.
  • To reduce memory requirements for self-learning control.
  • To improve the learning speed and scalability of self-learning control systems.

Main Methods:

  • The proposed technique integrates CMAC with a self-learning control scheme.
  • Learned information is distributively stored, rather than using one memory line per state.
  • CMAC's information interpolation capabilities are leveraged.

Related Experiment Videos

Main Results:

  • The integrated technique significantly reduces the memory required for self-learning control.
  • The approach enhances the applicability of self-learning control to larger and more complex problems.
  • Improved learning speed was observed due to CMAC's interpolation capabilities.

Conclusions:

  • Integrating CMAC offers a more memory-efficient and scalable solution for self-learning control.
  • The enhanced approach accelerates the learning process, making it suitable for larger problems.
  • This integration represents a significant advancement in the field of intelligent control systems.