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

Linear and quadratic programming neural network analysis.

C Y Maa1, M A Shanblatt

  • 1Electron. Data Syst., Auburn Hills, MI.

IEEE Transactions on Neural Networks
|January 1, 1992
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

Human-like dynamic programming neural networks for dynamic time warping speech recognition.

International journal of neural systems·1995
Same author

Random noise effects in pulse-mode digital multilayer neural networks.

IEEE transactions on neural networks·1995
Same author

Architecture and statistical model of a pulse-mode digital multilayer neural network.

IEEE transactions on neural networks·1995
Same author

A two-phase optimization neural network.

IEEE transactions on neural networks·1992
Same author

Energy function analysis of dynamic programming neural networks.

IEEE transactions on neural networks·1991
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

Neural networks are analyzed for solving linear and quadratic programming problems, extending optimization theory to tackle challenges like the least-squares problem. Network parameters allow control over solution accuracy for constrained and unconstrained optimization.

Area of Science:

  • Computational Mathematics
  • Optimization Theory
  • Neural Network Applications

Background:

  • Neural networks offer a dynamic approach to solving complex mathematical problems.
  • Existing networks require justification within optimization theory for broader applicability.
  • Optimization problems, including linear and quadratic programming, are fundamental in various scientific fields.

Purpose of the Study:

  • To analyze neural networks for linear and quadratic programming.
  • To justify the Kennedy-Chua neural network from an optimization theory perspective.
  • To extend the network's applicability to diverse optimization problems, including least-squares.

Main Methods:

  • Analysis of neural network dynamics for optimization.
  • Justification of the Kennedy-Chua network using optimization theory principles.

Related Experiment Videos

  • Extension of the network technique to least-squares and other C(2) convex objective function problems with linear constraints.

    • Main Results:

    • The neural network converges to an equilibrium or exact solution for quadratic programming, depending on constraints.
    • The approach provides an analytical method for solving linear systems (Bx=b) without matrix inversion.
    • Network parameter selection influences the distance between equilibria and problem solutions.

    Conclusions:

    • The analyzed neural networks are applicable to optimization problems with C(2) convex objective functions and linear constraints.
    • Simulation results demonstrate the dynamics and practical applicability of these networks.
    • The study validates a neural network approach for efficient optimization problem-solving.