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

Neural networks learning with sliding mode control: the sliding mode backpropagation algorithm.

G G Parma1, B R de Menezes, A P Braga

  • 1PARMA@CPDEE.UFMG.BR

International Journal of Neural Systems
|November 24, 1999
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

Shifts in plant respiration and carbon use efficiency at a large-scale drought experiment in the eastern Amazon.

The New phytologist·2010
Same author

A method for extracting plant roots from soil which facilitates rapid sample processing without compromising measurement accuracy.

The New phytologist·2007
Same author

Training SVMs with EDR algorithm.

International journal of neural systems·2001
Same author

Recent advances in the MOBJ algorithm for training artificial neural networks.

International journal of neural systems·2001
Same author

Inversion of simulated positron annihilation lifetime spectrum using a neural network.

Journal of chemical information and computer sciences·2001
Same author

Nonlinear system identification using a neo fuzzy neuron algorithm: electrical drive application.

International journal of neural systems·1999

Sliding mode control theory accelerates multi-layer perceptron training by adapting weights faster than standard backpropagation. This novel approach enhances learning speed and robustness in neural networks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Control Theory

Background:

  • Standard backpropagation algorithms for multi-layer perceptrons can be computationally intensive.
  • Adapting neural network weights efficiently is crucial for complex learning tasks.

Purpose of the Study:

  • To introduce sliding mode control theory as a novel technique for adapting weights in multi-layer perceptrons.
  • To demonstrate the efficacy of sliding mode control in accelerating neural network training.

Main Methods:

  • The study adapts classical backpropagation weight update equations.
  • Sliding mode control theory is integrated to modify weight adaptation processes.
  • A multi-layer perceptron architecture is utilized for experimentation.

Related Experiment Videos

Main Results:

  • The proposed sliding mode-based algorithm significantly increases the speed of learning compared to standard backpropagation.
  • The algorithm exhibits key characteristics of sliding mode control, including robustness.
  • High speed of learning is a notable outcome of the implemented method.

Conclusions:

  • Sliding mode control theory offers a powerful framework for training neural networks.
  • The integration of control theory principles enhances neural network performance, particularly in learning speed and robustness.
  • This research highlights a new direction for optimizing neural network training methodologies.