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

Extended Hopfield models for combinatorial optimization.

A Le Gall1, V Zissimopoulos

  • 1LRI, CNRS-URA 410, Bât 490, Université de Paris Sud, 91405 Orsay Cedex, France.

IEEE Transactions on Neural Networks
|February 7, 2008
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

A Global Geomorphologic Map of Saturn's Moon Titan.

Nature astronomy·2020
Same author

Using velocity-pressure loops in the operating room: a new approach of arterial mechanics for cardiac afterload monitoring under general anesthesia.

American journal of physiology. Heart and circulatory physiology·2019
Same author

New software dedicated to virtual mazes for human cognitive investigations.

Journal of neuroscience methods·2019
Same author

The critical role of vestibular graviception during cognitive-motor development.

Behavioural brain research·2019
Same author

Norepinephrine reduces arterial compliance less than phenylephrine when treating general anesthesia-induced arterial hypotension.

Acta anaesthesiologica Scandinavica·2017
Same author

Spectral properties of Titan's impact craters imply chemical weathering of its surface.

Geophysical research letters·2016
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 competitive activation mechanism to the extended Hopfield neural network, significantly reducing ambiguous neuron states for combinatorial optimization problems.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Operations Research

Background:

  • The extended Hopfield neural network (EHNN) by Abe et al. is used for combinatorial optimization but suffers from ambiguous neuron states.
  • This ambiguity can lead to suboptimal solutions in complex problem-solving.

Purpose of the Study:

  • To address the limitation of ambiguous neuron activations in the EHNN.
  • To improve the performance of EHNN in solving constrained combinatorial optimization problems.

Main Methods:

  • A competitive activation mechanism was introduced into the EHNN model.
  • A novel penalty energy expression was derived to manage neuron activation levels.
  • The enhanced model was experimentally validated on the set covering problem.

Related Experiment Videos

Main Results:

  • The modified EHNN significantly reduced the number of neurons with intermediate activation levels.
  • The competitive activation mechanism improved the network's ability to find stable, unambiguous states.
  • Experimental results on the set covering problem demonstrated the effectiveness of the proposed modifications.

Conclusions:

  • Competitive activation mechanisms are crucial for enhancing Hopfield neural network models.
  • The revised EHNN offers a more robust approach to solving constrained combinatorial optimization problems.
  • This work provides a valuable improvement for neural network-based optimization techniques.