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

An improved Voronoi-diagram-based neural net for pattern classification.

C Gentile1, M Sznaier

  • 1Wireless Communications Technologies Group, National Institute of Standards and Technology, Gaithersburg, MD 20899, USA. camillo@antd.nist.gov

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

Diffuse CD30-Positive Cutaneous Infiltrate in a Clinically Suspected Hidradenitis Suppurativa Lesion: Histopathologic and Diagnostic Challenges.

Journal of cutaneous pathology·2026
Same author

Silk fibroin increases the elasticity of alginate-gelatin hydrogels and regulates cardiac cell contractile function in cardiac bioinks.

Biofabrication·2024
Same author

Increasing Public Safety Broadband Network Resiliency Through Traffic Control.

Digital communications and networks·2024
Same author

Carotid intima media-thickness is increased in obese children metabolically healthy, metabolically unhealthy, and with metabolic syndrome, compared to the non-obese controls.

European review for medical and pharmacological sciences·2021
Same author

How social media meet patients’ questions: YouTube™ review for children oral thrush.

Journal of biological regulators and homeostatic agents·2018
Same author

How social media meet patients’ questions: YouTube™ review for mouth sores in children.

Journal of biological regulators and homeostatic agents·2018
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

We developed a new neural network for point queries in partitioned spaces, simplifying nearest neighbor clustering. This approach reduces neurons and eliminates a layer, improving efficiency without complex tuning.

Area of Science:

  • Computational geometry
  • Artificial intelligence
  • Machine learning

Background:

  • Point queries in partitioned spaces are crucial for tasks like nearest neighbor clustering.
  • Existing methods often rely on complex neural network architectures and iterative design processes.

Purpose of the Study:

  • To introduce a novel, efficient neural network architecture for point query problems in R(n) partitioned into polyhedral regions.
  • To simplify the design and implementation of neural networks for nearest neighbor clustering.

Main Methods:

  • A two-layer neural network design based on Voronoi diagrams.
  • Elimination of the second layer, reducing neuron count.
  • Precise calculation of neuron numbers and connection weights without iterative tuning.

Related Experiment Videos

Main Results:

  • Substantial reduction in the number of neurons required.
  • Complete elimination of the second neural network layer.
  • Simplified design process with precise parameter determination.

Conclusions:

  • The proposed neural network offers a more efficient and simplified solution for point queries and nearest neighbor clustering.
  • This method avoids trial-and-error iterations and ad hoc parameters, enhancing predictability and reducing computational cost.