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

Optimization via intermittency with a self-organizing neural network.

Terence Kwok1, Kate A Smith

  • 1School of Business Systems, Faculty of Information Technology, Monash University, Clayton, Victoria 3168, Australia. terence.kwok@infotech.monash.edu.au

Neural Computation
|September 15, 2005
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

The Frequency of Signs of Meibomian Gland Dysfunction in Children with Epidermolysis Bullosa.

Ophthalmology·2016
Same author

A noisy self-organizing neural network with bifurcation dynamics for combinatorial optimization.

IEEE transactions on neural networks·2004
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces a novel neural network technique using intermittency to escape local minima in combinatorial optimization. The method enables self-organizing networks to find global optima, demonstrated with the N-Queens problem.

Area of Science:

  • Artificial Intelligence
  • Computational Science
  • Complex Systems

Background:

  • Neural networks often converge to local minima in combinatorial optimization, hindering global solution discovery.
  • Escaping local minima is crucial for effective problem-solving in complex optimization tasks.

Purpose of the Study:

  • To propose a technique enabling self-organizing neural networks to escape local minima using intermittency.
  • To investigate novel search dynamics for visiting multiple global minima as meta-stable states.

Main Methods:

  • Utilizing the intermittency phenomenon in self-organizing neural networks.
  • Combining Kohonen-type competitive learning with iterated softmax functions near bifurcation.
  • Analyzing fractal characteristics (1/f signals) and power law distributions in meta-stable states.

Related Experiment Videos

Main Results:

  • Demonstrated a technique for neural networks to escape local minima and find global optima.
  • Observed novel search dynamics leading to meta-stable states representing global minima.
  • The N-Queens problem yielded 92 solutions for 8-Queens and 4024 for 17-Queens in a single run.

Conclusions:

  • The proposed intermittency-based technique effectively enhances neural network performance in combinatorial optimization.
  • The method exhibits fractal properties and power-law distributions, indicating robust meta-stable convergence.
  • This approach offers a promising direction for solving complex optimization problems more efficiently.