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

Recurrent neural network as a linear attractor for pattern association.

Ming-Jung Seow, Vijayan K Asari

    IEEE Transactions on Neural Networks
    |March 11, 2006
    PubMed
    Summary

    We introduce a linear attractor network for pattern association, modeling state-space pipelines with a recurrent neural network learning algorithm. This novel technique demonstrates suitability for multiple-valued pattern association tasks.

    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

    Extrapolation Convolution for Data Prediction on a 2-D Grid: Bridging Spatial and Frequency Domains With Applications in Image Outpainting and Compressed Sensing.

    IEEE transactions on neural networks and learning systems·2025
    Same author

    Microscopic nuclei classification, segmentation, and detection with improved deep convolutional neural networks (DCNN).

    Diagnostic pathology·2022
    Same author

    A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease.

    Diagnostics (Basel, Switzerland)·2022
    Same author

    Conditional generative adversarial network demosaicing strategy for division of focal plane polarimeters.

    Optics express·2020
    Same author

    Recurrent residual U-Net for medical image segmentation.

    Journal of medical imaging (Bellingham, Wash.)·2019
    Same author

    Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network.

    Journal of digital imaging·2019

    Area of Science:

    • Computational Neuroscience
    • Machine Learning

    Background:

    • Traditional pattern association methods struggle with complex, multi-valued data.
    • Modeling dynamic state-space trajectories is crucial for understanding sequential patterns.

    Discussion:

    • The proposed linear attractor network leverages state-space pipelines for pattern association.
    • A novel recurrent neural network learning algorithm employing least-squares estimation defines network dynamics.
    • Convergence regions are statistically defined based on input pattern characteristics.

    Key Insights:

    • The network effectively models sequential patterns as pipelines in state space.
    • The least-squares estimation approach enables efficient learning of network dynamics.
    • The method shows promise for multiple-valued pattern association tasks.

    Related Experiment Videos

    Outlook:

    • Further research can explore applications in complex sequence recognition and memory.
    • Optimizing network parameters for larger datasets and higher dimensions is a potential future direction.
    • Investigating the biological plausibility of the linear attractor model could yield new insights.