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

Separating figure from ground with a parallel network.

P K Kienker, T J Sejnowski, G E Hinton

    Perception
    |January 1, 1986
    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

    Presynaptic Vesicles Supply Membrane for Axonal Bouton Enlargement during Long Term Potentiation.

    The Journal of neuroscience : the official journal of the Society for Neuroscience·2026
    Same author

    Presynaptic vesicles supply membrane for axonal bouton enlargement during LTP.

    bioRxiv : the preprint server for biology·2025
    Same author

    Stochastic self-tuning hybrid algorithm for reaction-diffusion systems.

    The Journal of chemical physics·2020
    Same author

    A path toward understanding neurodegeneration.

    Science (New York, N.Y.)·2016
    Same author

    Disruption of mGluR5 in parvalbumin-positive interneurons induces core features of neurodevelopmental disorders.

    Molecular psychiatry·2015
    Same author

    Monitoring Spiking Activity of Many Individual Neurons in Invertebrate Ganglia.

    Advances in experimental medicine and biology·2015
    Same journal

    Predictive models and parameter analysis for multiple tactile perceptions in skin-wet fabrics interface.

    Perception·2026
    Same journal

    High-resolution kitsch by AI: Why society needs art, not more AI content.

    Perception·2026
    Same journal

    Benchmarking spatial discrimination thresholds of two-frame motion defined forms compared to luminance and stereoscopic defined forms.

    Perception·2026
    Same journal

    The effect of face masks on the perception of trustworthiness and competence in individuals with autistic traits.

    Perception·2026
    Same journal

    The importance of external features for categorizing ethnicity: can Koreans identify Korean, Japanese, and Chinese faces?

    Perception·2026
    Same journal

    Interoception, alexithymia, and motor congruency: Psychological drivers of body ownership in virtual reality.

    Perception·2026
    See all related articles

    This study models how the brain distinguishes figures from the background using a parallel network. Simulated annealing proved more robust than gradient descent for figure-ground segregation, even with incomplete outlines.

    Area of Science:

    • Computational Neuroscience
    • Computer Vision
    • Cognitive Science

    Background:

    • Figure-ground segregation is crucial for visual perception.
    • Rapid discrimination suggests parallel processing in the visual cortex.
    • Existing models often assume pre-segmented images.

    Purpose of the Study:

    • To simulate collective computation for figure-ground segregation using a parallel network.
    • To investigate the efficacy of gradient descent and simulated annealing for this task.
    • To explore the role of top-down attention in visual organization.

    Main Methods:

    • Designed a network of simple processing units.
    • Incorporated bottom-up image input and top-down attentional input.
    • Compared gradient descent (local optimization) and simulated annealing (global optimization with noise).

    Related Experiment Videos

    Main Results:

    • Simulated annealing was more robust, handling wider parameter ranges and incomplete outlines.
    • Gradient descent was faster for complete outlines but had a narrow success range.
    • The network demonstrated that global outline properties can emerge from local interactions.

    Conclusions:

    • A parallel network model can perform figure-ground segregation.
    • Simulated annealing offers a more robust approach for visual organization tasks.
    • Noise may be essential for escaping suboptimal solutions in complex visual processing.