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

Neural techniques for combinatorial optimization with applications.

K Smith1, M Palaniswami, M Krishnamoorthy

  • 1School of Business Systems, Monash University, Clayton, Victoria 3168, Australia.

IEEE Transactions on Neural Networks
|February 8, 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

Adjunctive therapy in epilepsy: a cost-effectiveness comparison of two AEDs.

Seizure·1999
Same author

Traumatic rupture of the aortic arch treated by stent grafting.

European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery·1999
Same author

Characteristics of protein and energy metabolism in neonates with necrotizing enterocolitis--a pilot study.

Journal of pediatric surgery·1999
Same author

Children's Defense Fund focuses Congress on child care: both sides of the aisle submit proposals.

Pediatric nursing·1999
Same author

Electrophysiological evidence of cortical fusion in children with early-onset esotropia.

Investigative ophthalmology & visual science·1999
Same author

Adenosine and pediatric supraventricular tachycardia in the emergency department: multicenter study and review.

Annals of emergency medicine·1999
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 novel neural network techniques to solve complex optimization problems, ensuring feasible solutions and broader applicability than existing methods.

Area of Science:

  • Artificial Intelligence
  • Computational Optimization
  • Operations Research

Background:

  • Neural networks offer solutions for NP-hard combinatorial optimization problems.
  • Existing methods like Hopfield networks and self-organizing maps have limitations, including infeasible solutions and restricted generalizability.
  • Overcoming these limitations is crucial for advancing computational optimization.

Purpose of the Study:

  • To propose novel neural network techniques that address the shortcomings of existing methods.
  • To develop a Hopfield network variant ensuring solution feasibility and improving quality by escaping local minima.
  • To create a generalized self-organizing neural network applicable to a wide range of combinatorial optimization problems.

Main Methods:

  • Development of an enhanced Hopfield network model.

Related Experiment Videos

  • Design of a generalized self-organizing neural network architecture.
  • Empirical testing on two practical optimization problems from Australian industry.
  • Comparison of proposed neural techniques against traditional heuristic solutions.

    • Main Results:

    • The proposed Hopfield network variant successfully ensures solution feasibility.
    • Improved solution quality was achieved by effectively escaping local minima.
    • The generalized self-organizing neural network demonstrated broad applicability to diverse combinatorial problems.
    • Neural techniques showed competitive or superior performance compared to traditional heuristics.

    Conclusions:

    • The novel neural network techniques effectively overcome the limitations of previous approaches.
    • These advancements offer more robust and generalizable solutions for NP-hard combinatorial optimization.
    • The findings have significant implications for applying advanced computational methods in industrial optimization challenges.