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 mixed analog/digital chaotic neuro-computer system for quadratic assignment problems.

Yoshihiko Horio1, Tohru Ikeguchi, Kazuyuki Aihara

  • 1Department of Electronic Engineering, Tokyo Denki University, 2-2 Kanda-Nishiki-cho, Chiyoda-ku, Tokyo 101-8457, Japan. horio@d.dendai.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|August 10, 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

CauFinder: Steering Cell-State and Phenotype Transitions by Causal Disentanglement Learning.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Identifying the optimal rapid antigen test for screening and determining the end of isolation: A modeling study.

PLoS computational biology·2026
Same author

Force Learning in Balanced Cortical E-I Networks.

Neural computation·2026
Same author

Psychological distress among Japanese high school students during the COVID-19 pandemic: An energy landscape analysis.

PLoS medicine·2026
Same author

Stratification of viral shedding patterns in saliva of COVID-19 patients.

eLife·2026
Same author

Brain-Inspired Chaotic Graph Backpropagation for Combinatorial Optimization.

IEEE transactions on neural networks and learning systems·2026

This study introduces an improved chaotic neuro-computer for solving complex quadratic assignment problems (QAPs). The new system successfully finds optimal solutions for QAPs, outperforming previous models.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Optimization

Background:

  • Quadratic Assignment Problems (QAPs) are NP-hard, posing significant challenges for real-world applications.
  • Previous Hopfield-type chaotic neuro-computers achieved good feasible solutions but struggled to find optimal QAP solutions.

Purpose of the Study:

  • To enhance the performance of chaotic neuro-computers for solving QAPs.
  • To develop a system capable of finding optimal solutions for QAPs.

Main Methods:

  • Constructed a mixed analog/digital chaotic neuro-computer prototype.
  • Implemented a novel solution construction method utilizing analog internal neuron states.
  • Integrated a multi-channel analog-to-digital conversion system to monitor neuron states.

Related Experiment Videos

Main Results:

  • Achieved significant performance improvement over the original chaotic neuro-computer.
  • Successfully obtained the optimal solution for a size-10 QAP within 1000 iterations.
  • Demonstrated the effectiveness of the solution construction method.

Conclusions:

  • The improved chaotic neuro-computer system effectively solves QAPs.
  • The proposed parameter tuning guideline aids in optimizing system performance.
  • This work advances the application of chaotic neural networks in combinatorial optimization.