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 architecture for pattern sequence verification through inferencing.

M J Healy1, T P Caudell, S G Smith

  • 1The Boeing Co., Seattle, WA.

IEEE Transactions on Neural Networks
|January 1, 1993
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

Impact of helminth co-infection and treatment on mycobacterial growth inhibition in UK migrants with TB infection.

IJTLD open·2025
Same author

The impact of mepolizumab on sleep impairment in CRSwNP: post hoc analyses of SYNAPSE and MUSCA.

Rhinology·2024
Same author

Mepolizumab improves sense of smell in severe chronic rhinosinusitis with nasal polyps: SYNAPSE.

Rhinology·2024
Same author

Evaluating treatment response to mepolizumab in patients with severe CRSwNP.

Rhinology·2023
Same author

Mepolizumab improves quality of life and reduces activity impairments in patients with CRSwNP.

Rhinology·2022
Same author

Early participant-reported symptoms as predictors of adherence to anastrozole in the International Breast Cancer Intervention Studies II.

Annals of oncology : official journal of the European Society for Medical Oncology·2017
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

LAPART, a neural network for logical inferencing, learns by verifying pattern pairs from experience. This architecture predicts and tests sequences, aiding in recognizing familiar patterns and flagging novel ones.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Traditional pattern recognition methods face challenges with sequential data.
  • Adaptive Resonance Theory (ART) networks offer a framework for stable learning.
  • Integrating ART networks can enhance logical inferencing capabilities.

Purpose of the Study:

  • Introduce LAPART, a novel neural network architecture.
  • Enable supervised learning and logical inferencing through pattern sequence verification.
  • Demonstrate LAPART's ability to predict and validate pattern sequences.

Main Methods:

  • Developed LAPART by interconnecting Adaptive Resonance Theory (ART) networks.
  • Implemented a predictive mechanism where the network infers and tests subsequent pattern classes.

Related Experiment Videos

  • Utilized a simulation involving a sequence of sensor images for target verification.

    • Main Results:

    • LAPART successfully learned to infer pattern classes and form predictive sequences.
    • Confirmed predictions aided in verifying familiar sequences.
    • Disconfirmed predictions effectively flagged novel pattern pairings.

    Conclusions:

    • LAPART provides a robust architecture for logical inferencing and supervised learning.
    • The network's predictive capabilities enhance pattern sequence recognition.
    • LAPART demonstrates potential for applications requiring real-time sequence analysis and verification.