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

Interpolating vectors for robust pattern recognition.

Kunihiko Fukushima1

  • 1Kansai University, Takatsuki, Osaka 569-1095, Japan. fukushima@m.ieice.org

Neural Networks : the Official Journal of the International Neural Network Society
|August 24, 2007
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

Efficient IntVec: High recognition rate with reduced computational cost.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

Introduction.

International journal of neural systems·2018
Same author

Margined winner-take-all: New learning rule for pattern recognition.

Neural networks : the official journal of the International Neural Network Society·2017
Same author

Training multi-layered neural network neocognitron.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

Artificial vision by multi-layered neural networks: neocognitron and its advances.

Neural networks : the official journal of the International Neural Network Society·2012
Same author

Increasing robustness against background noise: visual pattern recognition by a neocognitron.

Neural networks : the official journal of the International Neural Network Society·2011
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

This study introduces an interpolating vector algorithm for pattern recognition. The method significantly improved handwritten digit recognition accuracy by reducing the error rate.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Pattern recognition is crucial for various AI applications.
  • Existing methods face challenges in classification accuracy and efficiency.

Purpose of the Study:

  • To propose a novel algorithm for pattern recognition using interpolating vectors.
  • To enhance the performance of existing models like the neocognitron.

Main Methods:

  • Generating labeled reference vectors in a feature space via competitive learning.
  • Creating virtual interpolating vectors between reference vectors of the same class.
  • Classifying test vectors by selecting the most similar interpolating vector.

Main Results:

Related Experiment Videos

  • The algorithm was applied to the neocognitron for handwritten digit recognition.
  • Achieved a reduction in error rate from 1.52% to 1.02% on a 5000-digit test set.

Conclusions:

  • The interpolating vector algorithm offers a powerful and effective approach to pattern recognition.
  • Demonstrated significant improvements in handwritten digit recognition tasks.