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 layer neural networks for linear system identification using gradient descent technique.

S Bhama1, H Singh

  • 1Dept. of Electr. and Comput. Eng., Wayne State Univ., Detroit, MI.

IEEE Transactions on Neural Networks
|January 1, 1993
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

Sleep pattern and night awakening in healthy infants.

Indian pediatrics·1992
Same author

Spinal anaesthesia with lidocaine 2% for caesarean section.

Canadian journal of anaesthesia = Journal canadien d'anesthesie·1992
Same author

Peroxisomal beta-oxidation of branched chain fatty acids in human skin fibroblasts.

Journal of lipid research·1992
Same author

Effects of rat interleukin-2 and rat interferon on the natural killer cell activity of rat spleen cells after thermal injury.

The Journal of burn care & rehabilitation·1992
Same author

Polymeric hydrogels for soft contact lenses.

Journal of biomedical materials research·1992
Same author

Choice of toothbrush: a survey of dentists' personal preferences and recommendations for patients.

Australian dental journal·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 a gradient descent (GD) method using single-layer neural networks for linear dynamical system identification. This approach is simpler, faster, and more cost-effective than existing Hopfield network methods.

Area of Science:

  • * Control Engineering
  • * Computational Neuroscience
  • * Artificial Intelligence

Background:

  • * System identification is crucial for understanding and controlling dynamical systems.
  • * Neural networks offer a powerful tool for complex system modeling.
  • * Previous methods, like Hopfield networks, have implementation challenges.

Purpose of the Study:

  • * To present a gradient descent (GD) based method for linear dynamical system identification using single-layer neural networks.
  • * To demonstrate the advantages of this GD approach over existing techniques.

Main Methods:

  • * Utilized single-layer neural networks trained with the gradient descent (GD) algorithm.
  • * Applied the method to identify parameters of a linear time-invariant dynamical system.

Related Experiment Videos

  • * Mathematical formulation and network simulations were performed.

    • Main Results:

    • * The GD technique proved simpler and less hardware-intensive compared to Hopfield networks.
    • * The proposed neural network architecture is faster and suitable for online computation.
    • * Simulation results validated the effectiveness of the GD method for system identification.

    Conclusions:

    • * Gradient descent with single-layer neural networks is an efficient method for linear system identification.
    • * The parallel architecture and potential for analog components make it ideal for real-time applications.
    • * This approach offers a cost-effective and faster alternative for system identification problems.