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

Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions.

Sebastian Weng, Heiko Wersing, Jochen J Steil

    IEEE Transactions on Neural Networks
    |July 22, 2006
    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

    Generalization of finger-joint kinematics for cleaning tasks.

    Frontiers in robotics and AI·2026
    Same author

    ADMIRE: analysis of digitalized human-machine interactions and relations-looking closer at the tacit dimensions of human-machine relations as part of integrated research.

    Frontiers in robotics and AI·2026
    Same author

    The Epistemic Uncertainty Gradient in Spaces of Random Projections.

    Entropy (Basel, Switzerland)·2025
    Same author

    Comparative analysis of motor skill acquisition in a novel bimanual task: the role of mental representation and sensorimotor feedback.

    Frontiers in human neuroscience·2024
    Same author

    Exploring motor skill acquisition in bimanual coordination: insights from navigating a novel maze task.

    Scientific reports·2024
    Same author

    Face Generation and Editing With StyleGAN: A Survey.

    IEEE transactions on pattern analysis and machine intelligence·2024
    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

    This study introduces a hybrid learning method for image segmentation using recurrent neural networks and Hebbian learning. The approach successfully segments complex data, including medical cell images.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Computational Neuroscience

    Background:

    • Image segmentation is crucial for analyzing visual data.
    • Existing methods often struggle with complex feature binding and generalization.
    • Dynamic feature binding models offer a promising avenue for advanced segmentation.

    Purpose of the Study:

    • To develop a hybrid learning architecture for sophisticated image and feature segmentation.
    • To integrate recurrent neural networks, Hebbian learning, and vector quantization.
    • To apply the architecture to diverse segmentation challenges, including medical imaging.

    Main Methods:

    • A hybrid learning approach combining recurrent neural networks, unsupervised Hebbian learning, and vector quantization.
    • Utilizing the competitive layer model (CLM) as the core dynamic feature binding architecture.

    Related Experiment Videos

  • Employing Hebbian learning to set lateral weights for achieving target segmentation as attractor states.
  • Applying vector quantization to pair-wise feature relations for enhanced generalization.

    • Main Results:

    • Demonstrated successful application on artificial test examples.
    • Achieved accurate segmentation for a medical image analysis task involving fluorescence microscope cell images.
    • The architecture effectively handles perceptual grouping and segmentation problems.

    Conclusions:

    • The proposed hybrid learning method offers a robust and versatile solution for image and feature segmentation.
    • The integration of CLM with Hebbian learning and vector quantization enables sophisticated segmentation capabilities.
    • This approach shows significant potential for both general and specialized applications, particularly in medical image analysis.