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

Pattern classification by a condensed neural network.

A Mitiche1, M Lebidoff

  • 1INRS-Telecommunications, Place Bonaventure, Montreal, Quebec, Canada. mitiche@inrs-telecom.uquebec.ca

Neural Networks : the Official Journal of the International Neural Network Society
|June 20, 2001
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

A Kohonen neural network description of scoliosis fused regions and their corresponding Lenke classification.

International journal of computer assisted radiology and surgery·2012
Same author

Detection of edges using range information.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

On kineopsis and computation of structure and motion.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Computation of surface orientation and structure of objects using grid coding.

IEEE transactions on pattern analysis and machine intelligence·2011
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a condensed neural network combining neural network speed and nearest neighbor classifier accuracy. This novel approach offers a fast, accurate pattern classification method for applications like character recognition.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Neural networks are effective pattern classifiers, but can be slower than nearest neighbor (NN) classifiers.
  • Nearest neighbor classifiers offer high accuracy but can be computationally intensive.
  • A need exists for classifiers that balance speed and accuracy.

Purpose of the Study:

  • To investigate a condensed neural network architecture.
  • To combine the computational speed of neural networks with the low error rates of NN classifiers.
  • To develop a fast and accurate pattern classification system.

Main Methods:

  • Developed a condensed neural network comprising generalized perceptrons.
  • Utilized hyperspherical boundaries centered on memory units for classification.

Related Experiment Videos

  • Incorporated sporadic nearest neighbor matching for enhanced accuracy.
  • Compared the condensed network against Kohonen neural networks and NN classifiers.

    • Main Results:

    • The condensed network demonstrated a balance between speed and accuracy.
    • Achieved competitive performance in hand-printed character recognition tasks.
    • Showcased a simple architecture and function for efficient classification.

    Conclusions:

    • The condensed neural network presents a viable alternative for pattern classification.
    • Offers a promising approach for applications requiring both speed and high accuracy.
    • Potential for broader applications in machine learning and pattern recognition.