publication . Preprint . Other literature type . Article . 2018

Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks

Kailyn Schmidt; James J. DiCarlo; Pouya Bashivan; Kohitij Kar; Elias B. Issa; Rishi Rajalingham;
Open Access English
  • Published: 15 Aug 2018
  • Publisher: Cold Spring Harbor Laboratory
Abstract
<jats:title>ABSTRACT</jats:title><jats:p>Primates—including humans—can typically recognize objects in visual images at a glance even in the face of naturally occurring identity-preserving image transformations (e.g. changes in viewpoint). A primary neuroscience goal is to uncover neuron-level mechanistic models that quantitatively explain this behavior by predicting primate performance for each and every image. Here, we applied this stringent behavioral prediction test to the leading mechanistic models of primate vision (specifically, deep, convolutional, artificial neural networks; ANNs) by directly comparing their behavioral signatures against those of humans ...
Subjects
free text keywords: General Neuroscience, Research Articles, Pattern recognition, Artificial intelligence, business.industry, business, Computer science, Artificial neural network, Cognitive neuroscience of visual object recognition, Rhesus macaque, biology.organism_classification, biology, Behavioral pattern, Macaque, biology.animal, Evolution of color vision in primates, Primate, Categorization, Psychophysics, Binary Object
Funded by
NIH| The role of cortical feedback in visual face processing
Project
  • Funder: National Institutes of Health (NIH)
  • Project Code: 1K99EY022671-01
  • Funding stream: NATIONAL EYE INSTITUTE
,
NIH| The role of inferior temporal cortex in core visual object recognition
Project
  • Funder: National Institutes of Health (NIH)
  • Project Code: 2R01EY014970-11A1
  • Funding stream: NATIONAL EYE INSTITUTE

Kheradpisheh, S. R., et al. (2016). "Deep networks can resemble human feed-forward vision in invariant object recognition." Scientific reports 6: 32672. [OpenAIRE]

Abstract
<jats:title>ABSTRACT</jats:title><jats:p>Primates—including humans—can typically recognize objects in visual images at a glance even in the face of naturally occurring identity-preserving image transformations (e.g. changes in viewpoint). A primary neuroscience goal is to uncover neuron-level mechanistic models that quantitatively explain this behavior by predicting primate performance for each and every image. Here, we applied this stringent behavioral prediction test to the leading mechanistic models of primate vision (specifically, deep, convolutional, artificial neural networks; ANNs) by directly comparing their behavioral signatures against those of humans ...
Subjects
free text keywords: General Neuroscience, Research Articles, Pattern recognition, Artificial intelligence, business.industry, business, Computer science, Artificial neural network, Cognitive neuroscience of visual object recognition, Rhesus macaque, biology.organism_classification, biology, Behavioral pattern, Macaque, biology.animal, Evolution of color vision in primates, Primate, Categorization, Psychophysics, Binary Object
Funded by
NIH| The role of cortical feedback in visual face processing
Project
  • Funder: National Institutes of Health (NIH)
  • Project Code: 1K99EY022671-01
  • Funding stream: NATIONAL EYE INSTITUTE
,
NIH| The role of inferior temporal cortex in core visual object recognition
Project
  • Funder: National Institutes of Health (NIH)
  • Project Code: 2R01EY014970-11A1
  • Funding stream: NATIONAL EYE INSTITUTE

Kheradpisheh, S. R., et al. (2016). "Deep networks can resemble human feed-forward vision in invariant object recognition." Scientific reports 6: 32672. [OpenAIRE]

Any information missing or wrong?Report an Issue