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

An integrated network for invariant visual detection and recognition.

Yali Amit1, Massimo Mascaro

  • 1Department of Statistics, University of Chicago, Chicago, IL 60637, USA. amit@galton.uchicago.edu

Vision Research
|July 5, 2003
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

Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks.

Frontiers in computational neuroscience·2022
Same author

Deep Learning With Asymmetric Connections and Hebbian Updates.

Frontiers in computational neuroscience·2019
Same author

Inferring learning rules from distributions of firing rates in cortical neurons.

Nature neuroscience·2015
Same author

A Generative Statistical Algorithm for Automatic Detection of Complex Postures.

PLoS computational biology·2015
Same author

Memory capacity of networks with stochastic binary synapses.

PLoS computational biology·2014
Same author

Exome sequencing links corticospinal motor neuron disease to common neurodegenerative disorders.

Science (New York, N.Y.)·2014
Same journal

Editorial for VSI Amblyopia: Advances in Amblyopia Research.

Vision research·2026
Same journal

Computational and mathematical models in vision: Quantitative approaches to understanding visual perception.

Vision research·2026
Same journal

Complex interactions between lightness, chroma, and hue in color ensemble perception.

Vision research·2026
Same journal

Driving with autism spectrum disorder: Exploring the impact of tactile hazard warnings on gaze behavior and hazard responses.

Vision research·2026
Same journal

Early visual processing in adults with ADHD: evidence from contrast sensitivity, spatial integration, and external noise.

Vision research·2026
Same journal

Pupil reflexes generate the peripheral drift illusion due to ON/OFF motion responses.

Vision research·2026
See all related articles

This study introduces a novel visual processing architecture enabling invariant object detection and recognition. This system explains attentional mechanisms and neuronal responses observed in the visual cortex.

Area of Science:

  • Neuroscience
  • Computer Vision
  • Cognitive Science

Background:

  • Current models struggle with invariant visual recognition, particularly explaining attentional effects.
  • Understanding the neural basis of visual attention and object detection remains a challenge.

Purpose of the Study:

  • To propose a computational architecture for invariant visual detection and recognition.
  • To explain psychophysical and physiological observations related to attention and visual processing.
  • To hypothesize a neural mechanism for translation invariance in the visual cortex.

Main Methods:

  • Development of a novel computational architecture with a central learning module and a replica module.
  • Utilizing retinotopic layers and specific input/output designs for feature representation.

Related Experiment Videos

  • Simulating attentional mechanisms for location- or object-based processing.

    • Main Results:

    • The architecture allows for classification at specific locations or detection of all object instances.
    • It successfully explains object-based attention and response time differences in target detection.
    • The model accounts for observed attentional modulation of neuronal responses.

    Conclusions:

    • The proposed architecture provides a unified framework for invariant visual recognition and attention.
    • The columnar organization of the visual cortex may support the proposed copying mechanism for translation invariance.
    • This work offers insights into the neural computations underlying visual perception.