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

The diabolo classifier

Schwenk1

  • 1International Computer Science Institute, Berkeley CA, US, 1947 Center Street Suite 600, 94704. schwenk@icsi.berkeley.edu.

Neural Computation
|November 6, 1998
PubMed
Summary
This summary is machine-generated.

This study introduces a novel autoassociative neural network classifier for efficient pattern recognition. The new model achieves state-of-the-art optical character recognition results with low computational complexity.

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

Authors' reply

The British journal of surgery·2000
Same author

Ferromagnetic multilayers: Statics and dynamics.

Physical review. B, Condensed matter·1988
Same author

Superconductivity in sulfur-based organic superconductors: A volume property.

Physical review. B, Condensed matter·1986
Same author

Magnetic-field-induced transition and quantum oscillations in tetramethyltetraselenafulvalenium perrhenate, (TMTSF)2ReO4.

Physical review letters·1986
Same author

New, organic, volume superconductor at ambient pressure.

Physical review. B, Condensed matter·1985
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computer Vision

Background:

  • Traditional classifiers like nearest-neighbors and radial basis functions have limitations.
  • Developing efficient and accurate classification models is crucial for pattern recognition tasks.

Purpose of the Study:

  • To introduce a new classification architecture based on autoassociative neural networks.
  • To demonstrate its effectiveness in learning discriminant models for each class.
  • To highlight its advantages over existing model-based classifiers.

Main Methods:

  • Utilizing autoassociative neural networks to learn discriminant models.
  • Employing a compact, distributed representation for models.
  • Incorporating a priori knowledge via problem-specific distance measures, specifically tangent distance.

Related Experiment Videos

  • Applying the classifier to optical character recognition (OCR).

    • Main Results:

    • The proposed architecture exhibits low computational complexity.
    • It uses a compact and distributed representation of models.
    • Achieved state-of-the-art results on several optical character recognition databases.
    • Demonstrated successful incorporation of tangent distance for transformation invariance.

    Conclusions:

    • The autoassociative neural network classifier offers an efficient and effective approach to pattern recognition.
    • It provides a competitive alternative to existing classification methods, particularly in OCR.
    • The architecture's flexibility allows for the integration of prior knowledge, enhancing performance.