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 Concept Videos

Prosopagnosia01:24

Prosopagnosia

693
Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...
693
Neural Circuits01:25

Neural Circuits

2.6K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.6K
Visual Agnosia01:12

Visual Agnosia

957
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
957
Vision01:24

Vision

59.3K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
59.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

From body selectivity to socio-emotional meaning: where extrastriate body area stops.

Cerebral cortex (New York, N.Y. : 1991)·2026
Same author

Low-dimensional and optimised representations of high-level information in the expert brain.

Nature communications·2026
Same author

Tracing aesthetic experience from perception and conception to appraisal using deep convolutional neural networks.

iScience·2026
Same author

Can Category-selective Cortex Predict Categorization Behavior?

Journal of cognitive neuroscience·2026
Same author

Rethinking neuroaesthetics: Toward a multidimensional and integrative science of aesthetic experience.

Neuron·2026
Same author

Connecting the dots: Similar visual orthographic acquisition for Braille or line junctions.

Psychonomic bulletin & review·2026

Related Experiment Video

Updated: Jan 14, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Recurrent issues with deep neural network models of visual recognition.

Timothee Maniquet1, Hans Op de Beeck2, Andrea Ivan Costantino2

  • 1Leuven Brain Institute, KU Leuven, Leuven, Belgium. timotheemaniquet@gmail.com.

Scientific Reports
|October 17, 2025
PubMed
Summary

Recurrent deep neural networks (DNNs) show that model size, not recurrence, drives performance in object recognition tasks. Larger models better predict human difficulty, but recurrence negatively impacts confusion matrix matching.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Related Experiment Videos

Last Updated: Jan 14, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Area of Science:

  • Computational neuroscience
  • Cognitive science
  • Artificial intelligence

Background:

  • The ventral stream's recurrent connectivity provides robustness for object recognition in naturalistic settings.
  • Recurrent deep neural networks (DNNs) are emerging models of the ventral stream, outperforming feedforward DNNs in explaining brain representations.

Purpose of the Study:

  • To investigate if recurrent DNNs better model human behavior in visual recognition tasks compared to feedforward DNNs.
  • To explore the relationship between recurrence, model size, and performance in visual recognition.

Main Methods:

  • A stimulus set with challenges like occlusion, clutter, and scrambling was used.
  • Human participants performed a categorization task on the stimulus set, creating a benchmark dataset.
  • Various recurrent and feedforward DNN architectures were applied to the same task.

Main Results:

  • Model performance was most strongly correlated with model size, irrespective of architecture.
  • Larger models showed greater consistency with human perception of task difficulty across manipulations.
  • Recurrent DNNs, unlike feedforward ones, exhibited a negative effect of size on matching human confusion matrices.

Conclusions:

  • Model size, rather than recurrence, appears to be the primary driver of performance in these visual recognition models.
  • Recurrent DNNs may not be superior to feedforward DNNs for modeling human visual recognition behavior.
  • The complexity of incorporating recurrence into computational models needs further investigation.