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 model for category learning

D L Reilly, L N Cooper, C Elbaum

    Biological Cybernetics
    |January 1, 1982
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a neural model for supervised learning that effectively categorizes complex patterns using prototypes and adjustable weights. The model successfully defines nonlinear classification boundaries, improving pattern recognition capabilities.

    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

    Protein signaling and morphological development of the tail fluke in the embryonic beluga whale (Delphinapterus leucas).

    Developmental dynamics : an official publication of the American Association of Anatomists·2024
    Same author

    Author Correction: Universal DNA methylation age across mammalian tissues.

    Nature aging·2023
    Same author

    Universal DNA methylation age across mammalian tissues.

    Nature aging·2023
    Same author

    Methods and insights from the characterization of osteoprogenitor cells of bats (Mammalia: Chiroptera).

    Stem cell research·2016
    Same author

    Peak effect in polycrystalline vortex matter.

    Physical review letters·2007
    Same author

    Targeting c-Myc-activated genes with a correlation method: detection of global changes in large gene expression network dynamics.

    Proceedings of the National Academy of Sciences of the United States of America·2005
    Same journal

    Harmonic memory in phasor neural networks.

    Biological cybernetics·2026
    Same journal

    Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

    Biological cybernetics·2026
    Same journal

    Foundational issues of network models in biology.

    Biological cybernetics·2026
    Same journal

    Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

    Biological cybernetics·2026
    Same journal

    Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

    Biological cybernetics·2026
    Same journal

    Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

    Biological cybernetics·2026
    See all related articles

    Area of Science:

    • Computational Neuroscience
    • Machine Learning
    • Pattern Recognition

    Background:

    • Supervised learning models often struggle with complex, nonlinear data.
    • Existing methods may require extensive data or complex feature engineering.

    Purpose of the Study:

    • To present a general neural model for supervised learning of pattern categories.
    • To develop a model capable of resolving pattern classes with arbitrary boundaries.

    Main Methods:

    • The model utilizes a memory-based approach with class elements (prototypes).
    • Each prototype is associated with a modifiable scalar weighting factor (lambda) to set categorization thresholds.
    • Learning involves prototype commitment and adjustment of lambda factors to minimize classification errors.

    Related Experiment Videos

    Main Results:

    • The model successfully defined classification boundaries for complicated pattern regions.
    • Demonstrated ability to resolve pattern classes separated by nonlinear boundaries.

    Conclusions:

    • The proposed neural model offers a robust framework for supervised learning of complex pattern categories.
    • Discusses the potential role of divisive inhibition in neural network implementations.