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

Learning rules for neuro-controller via simultaneous perturbation.

Y Maeda1, R P De Figueiredo

  • 1Dept. of Electr. Eng., Kansai Univ., Osaka.

IEEE Transactions on Neural Networks
|January 1, 1997
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

A unified approach to optimal image interpolation problems based on linear partial differential equation models.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·1993
Same author

Neutralizing activity of human antibodies against the structural protein of human T-cell lymphotropic virus type I.

International journal of cancer·1992
Same author

[A new steroid therapy for difficult asthmatics--an induction and maintenance, two-step therapy].

Arerugi = [Allergy]·1992
Same author

Development of a mandibular tracking device with six degrees of freedom using optoelectronic system.

The Journal of Osaka University Dental School·1992
Same author

The changes in body temperature, oxygen consumption, CO2 production and muscle protein turnover rate by selection for body size in Japanese quail, Coturnix coturnix japonica.

Comparative biochemistry and physiology. Comparative physiology·1992
Same author

Tumor dormancy and the effect of selected drugs on the tumor-dormant state.

Laboratory animal science·1992
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 introduces novel learning rules for neurocontrollers that do not require knowledge of the plant's sensitivity function. These simultaneous perturbation methods enable effective control of unknown systems.

Area of Science:

  • Robotics
  • Control Systems Engineering
  • Artificial Intelligence

Background:

  • Direct control schemes using neural networks often necessitate learning an inverse model of the unknown plant.
  • Traditional learning rules, like gradient methods, require knowledge of the plant's sensitivity function.

Purpose of the Study:

  • To develop and describe new learning rules for neurocontrollers that circumvent the need for sensitivity function information.
  • To demonstrate the efficacy of these novel learning rules in controlling unknown dynamic systems.

Main Methods:

  • Simultaneous perturbation methods are employed as the learning rule for the neurocontroller.
  • The approach avoids explicit calculation or knowledge of the plant's sensitivity function.

Related Experiment Videos

Main Results:

  • Numerical simulations showcase successful application to a two-link planar arm.
  • The method effectively addresses a tracking problem for a nonlinear dynamic plant.

Conclusions:

  • The proposed learning rules offer a viable alternative for neurocontroller design when plant sensitivity is unknown.
  • Simultaneous perturbation learning provides a practical approach for adaptive control of complex systems.