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

A novel neural network for nonlinear convex programming.

Xing-Bao Gao1

  • 1College of Mathematics and Information Science, Shaanxi Normal University, Xi'an, Shaanxi 710062, PR China. xin-baog@snnu.edu.cn

IEEE Transactions on Neural Networks
|September 24, 2004
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

[On-site measurement of landfill gas yield and verification of IPCC model].

Huan jing ke xue= Huanjing kexue·2010
Same author

A new projection-based neural network for constrained variational inequalities.

IEEE transactions on neural networks·2009
Same author

[Chelating stabilization of heavy metals in fly ash from municipal solid waste incinerators for co-disposal in sanitary landfill].

Huan jing ke xue= Huanjing kexue·2008
Same author

[Extraction procedure for leaching toxicity of fly ash from municipal solid waste incinerators under Co-disposal scenario in landfill].

Huan jing ke xue= Huanjing kexue·2008
Same author

[Characterization and heavy metals leaching toxicity of fly ash from municipal solid waste incinerators in China].

Huan jing ke xue= Huanjing kexue·2008
Same author

A high-performance feedback neural network for solving convex nonlinear programming problems.

IEEE transactions on neural networks·2008
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 novel neural network for real-time nonlinear convex programming. The network efficiently solves problems by converting them into variational inequalities, offering a simpler and more stable alternative.

Area of Science:

  • * Optimization Theory
  • * Computational Neuroscience
  • * Applied Mathematics

Background:

  • * Nonlinear convex programming problems are prevalent in various scientific and engineering fields.
  • * Existing neural network approaches often require Lipschitz conditions or adjustable parameters, limiting their applicability.
  • * Real-time solutions for these complex optimization problems are highly desirable.

Purpose of the Study:

  • * To propose a novel neural network for solving nonlinear convex programming problems in real time.
  • * To demonstrate the network's stability and convergence properties.
  • * To offer an improved alternative to existing neural network methods.

Main Methods:

  • * Conversion of the nonlinear convex programming problem into a variational inequality problem.

Related Experiment Videos

  • * Construction of a dynamical system and a convex energy function for the variational inequality.
  • * Analysis of the neural network's stability using Lyapunov stability theory.

    • Main Results:

    • * The proposed neural network converges to an exact optimal solution for nonlinear convex programming.
    • * The network exhibits Lyapunov stability.
    • * Simulation results validate the network's performance and transient behavior.

    Conclusions:

    • * The developed neural network provides an effective and stable method for real-time nonlinear convex programming.
    • * It overcomes limitations of existing methods by not requiring Lipschitz conditions or adjustable parameters.
    • * The simplified structure and proven convergence make it a valuable tool for optimization tasks.