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

Hierarchical models of object recognition in cortex.

M Riesenhuber1, T Poggio

  • 1Department of Brain and Cognitive Sciences, Center for Biological and Computational Learning and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts 02142, USA.

Nature Neuroscience
|October 20, 1999
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

Correction: Excess of NPM-ALK oncogenic signaling promotes cellular apoptosis and drug dependency.

Oncogene·2025
Same author

An analysis of training and generalization errors in shallow and deep networks.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

Response from sinha and poggio.

Trends in cognitive sciences·2011
Same author

Multiclass cancer diagnosis using tumor gene expression signatures.

Proceedings of the National Academy of Sciences of the United States of America·2001
Same author

Learning in brains and machines.

Spatial vision·2001
Same author

Categorical representation of visual stimuli in the primate prefrontal cortex.

Science (New York, N.Y.)·2001

We present a new hierarchical model for visual object recognition, extending the classic simple to complex cell model. This biologically plausible model uses a MAX-like operation for advanced visual processing in the cortex.

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Computer Vision

Background:

  • Classical models of visual processing, like Hubel and Wiesel's simple and complex cells, describe a hierarchy of representations.
  • However, quantitative models exploring the biological feasibility of these hierarchical approaches for higher-level tasks like object recognition are scarce.

Purpose of the Study:

  • To develop and present a novel hierarchical computational model for object recognition.
  • To ensure the model is consistent with physiological data from the inferotemporal cortex.
  • To make testable predictions about neural function.

Main Methods:

  • Proposed a new hierarchical model for visual processing.
  • Incorporated a MAX-like operation on neuronal inputs.

Related Experiment Videos

  • Ensured consistency with physiological data from the inferotemporal cortex.

    • Main Results:

    • The developed hierarchical model successfully accounts for complex visual tasks such as object recognition.
    • The model is biologically plausible and consistent with known physiological data.
    • The model generates specific, testable predictions.

    Conclusions:

    • A novel hierarchical model, utilizing a MAX-like operation, provides a biologically plausible framework for object recognition.
    • This model extends classical visual processing theories and offers testable hypotheses for cortical function.