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

Graph partitioning using annealed neural networks.

D E Van den Bout1, T K Miller

  • 1Dept. of Electr. and Comput. Eng., North Carolina State Univ., Raleigh, NC.

IEEE Transactions on Neural Networks
|January 1, 1990
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

fos-1, a putative histidine kinase as a virulence factor for systemic aspergillosis.

Medical mycology·2002
Same author

COS-l, a putative two-component histidine kinase of Candida albicans, is an in vivo virulence factor.

Medical mycology·2001
Same author

The isolation of FOS-1, a gene encoding a putative two-component histidine kinase from Aspergillus fumigatus.

Fungal genetics and biology : FG & B·2000
Same author

Characterization and optimization of in vitro assay conditions for (1,3)beta-glucan synthase activity from Aspergillus fumigatus and Candida albicans for enzyme inhibition screening.

The Journal of antibiotics·1998
Same author

Inhibition of Neurospora crassa growth by a glucan synthase-1 antisense construct.

Current microbiology·1997
Same author

Effect of form of nitrogen on growth of ruminal microbes in continuous culture.

Journal of animal science·1996
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 algorithm, mean field annealing (MFA), significantly accelerates graph partitioning compared to simulated annealing (SA). This method enhances neural network convergence while maintaining solution quality and extends to multi-bin partitioning challenges.

Area of Science:

  • Computational Mathematics
  • Artificial Intelligence
  • Network Science

Background:

  • Graph partitioning is a fundamental problem in computer science with applications in various fields.
  • Existing algorithms like simulated annealing (SA) and neural networks have limitations in terms of convergence speed and solution quality.
  • Neural networks struggle with partitioning graphs into more than two bins.

Purpose of the Study:

  • To introduce and evaluate a new algorithm, mean field annealing (MFA), for graph partitioning.
  • To combine the strengths of simulated annealing and Hopfield neural networks.
  • To address the challenge of partitioning graphs into multiple bins.

Main Methods:

  • Application of the mean field annealing (MFA) algorithm to graph partitioning problems.

Related Experiment Videos

  • Comparison of MFA's performance against simulated annealing (SA).
  • Development of a modified MFA to support multi-bin graph partitioning.

    • Main Results:

    • MFA demonstrates 10-100 times faster convergence than SA for graph bipartitioning with comparable solution quality.
    • A modified MFA effectively handles partitioning graphs into three or more bins.
    • Analysis reveals a critical temperature in MFA's optimization process, analogous to neural network gain.

    Conclusions:

    • MFA offers a significant improvement in speed for graph partitioning while preserving solution quality.
    • The modified MFA extends the applicability of neural network-based approaches to multi-bin graph partitioning.
    • Understanding MFA's temperature behavior provides insights for tuning neural network performance.