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 neural network for shortest path computation.

F Araújo1, B Ribeiro, L Rodrigues

  • 1Faculdade de Ciências of Universidade de Lisboa, 1749-016 Lisboa, Portugal.

IEEE Transactions on Neural Networks
|February 6, 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

Pedigree-based assessment of genetic structure and disease-associated variants in friesian horses in Brazil.

Journal of equine veterinary science·2026
Same author

Soil and Genotype Shape the Sugarcane Phytobiome for Enhanced Environmental Adaptation.

Environmental microbiology reports·2026
Same author

Unlocking the potential of digital health in Portuguese cardiovascular disease management.

Revista portuguesa de cardiologia : orgao oficial da Sociedade Portuguesa de Cardiologia = Portuguese journal of cardiology : an official journal of the Portuguese Society of Cardiology·2025
Same author

Comparing the number of landmark points used to create statistical shape models of the lumbar spine from MR images.

Radiography (London, England : 1995)·2025
Same author

Plasma metabolomic profiles reveal sex-specific response to an oral glucose tolerance test in late middle-aged adults.

Mechanisms of ageing and development·2025
Same author

Enhanced collagen deposition in chondrogenic inflammation with Ibuprofen-specifically loaded chitosan/poly-gamma-glutamic acid nanoparticles.

International journal of pharmaceutics·2025
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 two-layer neural network enhances shortest path routing reliability and convergence for inter-network communication. This approach improves successful convergence in specific graph types, offering better performance.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Network Engineering

Background:

  • The shortest path problem is crucial for efficient inter-network routing.
  • Traditional Hopfield networks have limitations in reliable convergence for routing solutions.
  • Existing methods often lack guaranteed constraint satisfaction for valid shortest paths.

Purpose of the Study:

  • To introduce a new two-layer neural network architecture for solving the shortest path problem.
  • To enhance the reliability and successful convergence of routing solutions.
  • To address limitations in constraint satisfaction and convergence of previous methods.

Main Methods:

  • Extension of the single-layer recurrent Hopfield architecture to a two-layer system.
  • Implementation of automatic constraint satisfaction for valid shortest path solutions.

Related Experiment Videos

  • Comparative analysis of the proposed network against traditional methods on various graph classes.

    • Main Results:

    • The two-layer network demonstrates improved successful convergence for certain graph types.
    • Experimental results indicate enhanced reliability in finding valid shortest paths.
    • A trade-off was observed, with improved convergence at the cost of slightly degraded solution quality in some cases.

    Conclusions:

    • The proposed two-layer neural network offers a more reliable approach to solving the shortest path problem in inter-network routing.
    • This architecture effectively guarantees solution constraints, overcoming limitations of prior models.
    • Further research can explore optimizing the performance-quality trade-off for broader applicability.