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 bridge from syntactic to statistical pattern recognition.

Frank T. Allen1, Jason M. Kinser, H John Caulfield

  • 1Center for Applied Optical Sciences, Alabama A&M University, PO Box 1268, Normal, USA

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
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

Optical high-performance computing: introduction to the JOSA A and Applied Optics feature.

Applied optics·2009
Same author

Optical high-performance computing-JOSA A and Applied Optics: introduction.

Journal of the Optical Society of America. A, Optics, image science, and vision·2009
Same author

Discrimination among similar looking noisy color patches using Margin Setting.

Optics express·2009
Same author

Emmett Leith: a personal perspective.

Applied optics·2008
Same author

Manipulating light waves: introduction.

Applied optics·2008
Same author

Interference fringe analysis based on centroid detection.

Applied optics·2007
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

Syntactic pattern recognition uses feature relationships, unlike statistical methods. This paper introduces a pulse-coupled neural network (PCNN) that generates icons for statistical pattern recognition.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Pattern recognition encompasses both statistical and syntactic approaches.
  • Syntactic pattern recognition uniquely incorporates relationships among features within a dataset.
  • Statistical pattern recognition focuses primarily on feature sets without explicit relational information.

Purpose of the Study:

  • To introduce a novel application of pulse-coupled neural networks (PCNNs) in pattern recognition.
  • To demonstrate how PCNNs can bridge the gap between syntactic and statistical pattern recognition methods.
  • To generate feature representations (icons) suitable for subsequent statistical analysis.

Main Methods:

  • Utilized a pulse-coupled neural network (PCNN) architecture.

Related Experiment Videos

  • Employed syntactic processing within the PCNN to identify and encode feature relationships.
  • Generated output icons representing the syntactic structure of the input data.

    • Main Results:

    • The PCNN successfully produced icons that encapsulate feature relationships.
    • The generated icons are optimized for subsequent statistical pattern recognition tasks.
    • Demonstrated a viable method for integrating syntactic information into a statistically tractable format.

    Conclusions:

    • Pulse-coupled neural networks offer a powerful tool for syntactic pattern recognition.
    • The PCNN-generated icons provide an effective intermediate representation for hybrid recognition systems.
    • This approach enhances the capabilities of statistical pattern recognition by incorporating relational data.