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 two-phase optimization neural network.

C Y Maa1, M A Schanblatt

  • 1Electronic Data Systems, 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

Linear and quadratic programming neural network analysis.

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

A novel two-phase neural network precisely solves optimization problems, including those with boundary solutions, unlike prior methods. This network also automatically calculates Lagrange multipliers for constrained optimization tasks.

Area of Science:

  • Computational mathematics
  • Artificial intelligence
  • Optimization theory

Background:

  • Existing neural networks offer approximate solutions for optimization problems.
  • Constrained optimization problems with boundary solutions pose a significant challenge.

Purpose of the Study:

  • Introduce a novel two-phase neural network for optimization.
  • Enable exact solutions for constrained optimization problems, even at boundaries.
  • Simultaneously solve primal and dual problems in linear programming.

Main Methods:

  • Development of a two-phase neural network architecture.
  • Application to both constrained and unconstrained optimization.
  • Integration of Lagrange multiplier calculation.

Related Experiment Videos

Main Results:

  • The network achieves exact solutions for optimization problems, including boundary cases.
  • Phase-one network structure suffices for interior solutions.
  • Automatic computation of Lagrange multipliers is demonstrated.

Conclusions:

  • The proposed two-phase neural network offers superior accuracy for optimization.
  • It provides a unified framework for solving primal and dual linear programming problems.
  • This advancement enhances capabilities in solving complex optimization tasks.