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 competitive-layer model for feature binding and sensory segmentation.

H Wersing1, J J Steil, H Ritter

  • 1HONDA R&D Europe Germany, Carl-Legien-Str. 30, 63073 Offenbach/Main, Germany.

Neural Computation
|February 15, 2001
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

High adherence to anti-tuberculosis treatment among patients attending a hospital and slum health centre in Nairobi, Kenya.

Global public health·2024
Same author

A helium-burning white dwarf binary as a supersoft X-ray source.

Nature·2023
Same author

Canadian Cancer Trials Group (CCTG) IND215: A phase Ib study of Selumetinib in patients with untreated advanced or metastatic NSCLC who are receiving standard chemotherapy regimens.

Investigational new drugs·2018
Same author

Experimental amine-epoxide sealer: a physicochemical study in comparison with AH Plus and EasySeal.

International endodontic journal·2014
Same author

Crassulacean acid metabolism (CAM) in leaves of Aloe arborescens mill : Comparative studies of the carbon metabolism of chlorenchym and central hydrenchym.

Planta·2013
Same author

Anxiety.

Journal of religion and health·2013

We introduce the competitive-layer model (CLM), a novel recurrent neural network for feature binding and sensory segmentation. This model effectively groups input features using competitive and cooperative interactions, outperforming existing methods.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Computer Vision

Background:

  • Feature binding and sensory segmentation are crucial for understanding complex visual scenes.
  • Existing models often struggle to flexibly integrate grouping and segmentation processes.

Purpose of the Study:

  • To introduce a novel recurrent neural network, the competitive-layer model (CLM), for feature binding and sensory segmentation.
  • To demonstrate the CLM's ability to partition input features into salient groups using competitive and cooperative interactions.

Main Methods:

  • The CLM employs a layered network with topographically structured competitive and cooperative interactions.
  • Neural dynamics are formulated using additive recurrent networks with linear threshold neurons and pairwise compatibilities.

Related Experiment Videos

  • Dynamical winner-take-all circuits and deterministic annealing are utilized for robust grouping and convergence.

    • Main Results:

    • The CLM successfully partitions input features into salient groups, integrating figure-ground segmentation and grouping.
    • Analytic results on convergence and stable attractors generalize existing winner-take-all network findings.
    • The model demonstrates flexible response properties by exploiting amplitude information in grouping.

    Conclusions:

    • The competitive-layer model (CLM) offers a unified approach to feature binding, sensory segmentation, and contour detection.
    • Its dynamics provide robust and flexible grouping capabilities, advancing computational models of perception.
    • The CLM's analytic properties and integration capabilities represent a significant step in neural network research for vision.