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 coupled gradient network approach for static and temporal mixed-integer optimization.

P B Watta1, M H Hassoun

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

IEEE Transactions on Neural Networks
|January 1, 1996
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

Optical threshold logic elements for digital computation.

Optics letters·2009
Same author

A two-level hamming network for high performance associative memory.

Neural networks : the official journal of the International Neural Network Society·2001
Same author

Recurrent neural nets as dynamical Boolean systems with application to associative memory.

IEEE transactions on neural networks·1997
Same author

Solving problems in environmental engineering and geosciences with artificial neural networks [books.

IEEE transactions on neural networks·1996
Same author

Neurocontrollers trained with rules extracted by a genetic assisted reinforcement learning system.

IEEE transactions on neural networks·1995
Same author

NNERVE: neural network extraction of repetitive vectors for electromyography--Part I: Algorithm.

IEEE transactions on bio-medical engineering·1994
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

New artificial neural network methods offer parallelizable solutions for constrained mixed-integer optimization problems, enhancing global optimality with integrated search mechanisms.

Area of Science:

  • Computational Science and Engineering
  • Artificial Intelligence
  • Operations Research

Background:

  • Traditional mathematical programming methods for constrained mixed-integer optimization are often sequential and computationally intensive.
  • Existing approaches may lack efficient mechanisms for incorporating global search strategies, potentially limiting solution quality.

Purpose of the Study:

  • To introduce novel solution methodologies for constrained mixed-integer optimization problems leveraging artificial neural networks.
  • To develop methods that are amenable to parallel computation and facilitate the incorporation of global search mechanisms.
  • To extend these methods for addressing temporal mixed-integer optimization challenges.

Main Methods:

  • Artificial neural networks, specifically coupled gradient-type networks, are employed.

Related Experiment Videos

  • A penalty function approach is utilized to define network architecture, energy function, and dynamics.
  • Global search mechanisms are integrated into the computational framework.
  • The approach is extended to handle temporal optimization problems.

    • Main Results:

    • The proposed neural network-based methods demonstrate suitability for parallel implementation, outperforming sequential approaches.
    • The integration of global search mechanisms leads to more globally optimal solutions.
    • Simulations confirm the effectiveness of the coupled gradient network for both static and temporal mixed-integer optimization problems.

    Conclusions:

    • Artificial neural networks provide a powerful framework for developing efficient and parallelizable solution methods for constrained mixed-integer optimization.
    • The proposed approach enhances solution quality through integrated global search capabilities.
    • The methodology is versatile, extending to complex temporal optimization tasks.