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

Models of object recognition.

M Riesenhuber1, T Poggio

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

Nature Neuroscience
|December 29, 2000
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

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

Multiclass cancer diagnosis using tumor gene expression signatures.

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

Categorical representation of visual stimuli in the primate prefrontal cortex.

Science (New York, N.Y.)·2001
Same author

Learning in brains and machines.

Spatial vision·2001
Same author

Hierarchical models of object recognition in cortex.

Nature neuroscience·1999
Same author

Top-down learning of low-level vision tasks.

Current biology : CB·1998
Same journal

Hippocampal theta sweeps indicate goal direction during navigation.

Nature neuroscience·2026
Same journal

Goal-directed hippocampal theta sweeps during memory-guided navigation.

Nature neuroscience·2026
Same journal

Connectomic evidence that ordered activity drives neuromuscular network formation.

Nature neuroscience·2026
Same journal

Noninvasive decoding of typed sentences from human brain activity.

Nature neuroscience·2026
Same journal

Striatal control of amygdalar acetylcholine release during salience-associated processing.

Nature neuroscience·2026
Same journal

Conditioned accumbal dopamine transients forecast individual preference for drug versus natural rewards and compulsive behavior.

Nature neuroscience·2026
See all related articles

Biological visual systems recognize objects using models that balance specificity and invariance. Feedforward, view-based models align with psychophysical and physiological data for object recognition tasks.

Area of Science:

  • Computational neuroscience
  • Computer vision
  • Cognitive science

Background:

  • Object recognition is a key challenge in understanding biological visual systems.
  • Computational models aim to replicate human object recognition capabilities.
  • Different tasks like categorization and identification involve trade-offs between specificity and invariance.

Purpose of the Study:

  • To explore computational models for object recognition.
  • To determine if different recognition tasks require different model classes.
  • To focus on feedforward, view-based models supported by empirical data.

Main Methods:

  • Review of recent trends in computational vision.
  • Analysis of feedforward, view-based computational models.

Related Experiment Videos

  • Evaluation of model support from psychophysical and physiological data.

    • Main Results:

    • Categorization and identification tasks do not necessitate distinct model classes.
    • Feedforward, view-based models offer a viable computational approach.
    • These models are consistent with existing biological and behavioral evidence.

    Conclusions:

    • A unified class of models can address various object recognition tasks.
    • Feedforward, view-based architectures are promising for computational neuroscience.
    • Further research should explore these models' biological plausibility and performance.