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

Single net indirect learning architecture.

H C Andersen1, F C Teng, A C Tsoi

  • 1Dept. of Electr. and Comput. Eng., Queensland Univ., Brisbane, Qld.

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

Small beams, fast predictions: a comparison of machine learning dose prediction models for proton minibeam therapy.

Medical physics·2022
Same author

FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling.

Neural computation·2019
Same author

Experimental histological studies on the labyrinth; anaphylaxis.

Acta oto-laryngologica·2010
Same author

Experimental histological labyrinth examinations.

Acta oto-laryngologica·2010
Same author

The material of infant patients with otitis media in the Kommunehospital of Copenhagen.

Acta oto-laryngologica·2010
Same author

A simple carbon dioxide vapor pressure thermometer.

The Review of scientific instruments·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

This study introduces a new indirect learning architecture using a single neural network. This novel design reduces neuron and connection weight requirements by half for efficient controller training.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Control Systems Engineering

Background:

  • Indirect learning architectures are crucial for training controllers in complex systems.
  • Traditional methods often require significant computational resources and complex network structures.

Purpose of the Study:

  • To present a novel, simplified indirect learning architecture.
  • To reduce the number of neurons and connection weights in controller implementation.
  • To demonstrate the architecture's effectiveness in controlling nonlinear plants.

Main Methods:

  • Implementation of a single neural network for the indirect learning architecture.
  • Innovative design of an error signal generation mechanism using a memory element and switches.
  • Comparative analysis of the new architecture against the original indirect learning approach.

Related Experiment Videos

Main Results:

  • The novel architecture successfully generates the required error signal for controller training.
  • The new controller utilizes approximately half the neurons and connection weights compared to the original architecture.
  • Simulation results validate the controller's performance in managing a nonlinear plant.

Conclusions:

  • The proposed single-neural-network indirect learning architecture offers a more efficient and streamlined approach.
  • This method significantly reduces computational complexity and resource requirements.
  • The architecture is effective for controlling nonlinear systems, paving the way for more accessible advanced control solutions.