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

Visual System01:26

Visual System

692
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
692
Vision01:24

Vision

55.3K
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.
55.3K
Neural Circuits01:25

Neural Circuits

1.6K
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...
1.6K
Visual Agnosia01:12

Visual Agnosia

304
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...
304
Introduction to Learning01:18

Introduction to Learning

533
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
533
Associative Learning01:27

Associative Learning

579
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
579

You might also read

Related Articles

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

Sort by
Same author

Clinical Presentation of Pediatric Mycoplasma pneumoniae Before and After the COVID-19 Pandemic.

The Pediatric infectious disease journal·2025
Same author

The Pre-synaptic Landscape of Mitral/Tufted Cells of the Main Olfactory Bulb.

Frontiers in neuroanatomy·2019
Same author

Understanding Blind Deconvolution Algorithms.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

SPRINT: side-chain prediction inference toolbox for multistate protein design.

Bioinformatics (Oxford, England)·2010
Same author

Minimizing and learning energy functions for side-chain prediction.

Journal of computational biology : a journal of computational molecular cell biology·2008
Same author

A closed-form solution to natural image matting.

IEEE transactions on pattern analysis and machine intelligence·2007
Same journal

Visual Perception of Intuitive Physics and Its Computational Foundations.

Annual review of vision science·2026
Same journal

Diversity and Feature Selectivity of Primate Retinal Ganglion Cells.

Annual review of vision science·2026
Same journal

Predictive Foveal Processing in Active Vision.

Annual review of vision science·2026
Same journal

The Legacy of Perley G. Nutting Jr.: The Past and the Present of Chromatic Discrimination.

Annual review of vision science·2026
Same journal

Approaching Visual Perception with Spatiotemporally Patterned Optogenetic Stimulation.

Annual review of vision science·2026
Same journal

Ecological Vision Hypothesis: Training Deep Neural Networks for Robustness and Human Alignment.

Annual review of vision science·2026
See all related articles

Related Experiment Video

Updated: Sep 13, 2025

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

637

What Do Visual Neural Networks Learn?

Daniella Har-Shalom1,2, Yair Weiss1,2

  • 1School of Computer Science and Engineering, Hebrew University of Jerusalem, Jerusalem, Israel;

Annual Review of Vision Science
|July 29, 2025
PubMed
Summary
This summary is machine-generated.

Visual neural networks (VNNs) excel at classifying internet images using low-level cues. However, these artificial intelligence models struggle with variations that humans easily handle, indicating differences from human vision.

Keywords:
computer visionconvolutional neural networksrobustnessvision transformers

More Related Videos

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

565
Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.9K

Related Experiment Videos

Last Updated: Sep 13, 2025

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

637
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

565
Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.9K

Area of Science:

  • Computer Vision
  • Cognitive Science
  • Artificial Intelligence

Background:

  • Artificial neural networks (ANNs) demonstrate remarkable image classification performance, nearing human capabilities.
  • These ANNs are increasingly proposed as models for understanding human visual processing.

Purpose of the Study:

  • To review experimental evidence on the classification strategies of visual neural networks (VNNs).
  • To compare VNN strategies with human vision and traditional computer vision approaches.

Main Methods:

  • Evaluating VNN performance on tasks designed to reveal their learned cues.
  • Analyzing VNN responses to image manipulations and comparing them to human object recognition.

Main Results:

  • VNNs are susceptible to minor image changes (e.g., pixel alterations, background/illumination shifts) that do not affect human recognition.
  • VNNs exhibit invariance to significant image manipulations (e.g., random patch permutation) that impair human performance.

Conclusions:

  • VNNs learn low-level features highly effective for internet image classification.
  • The learned strategies differ from human vision, which exhibits greater robustness and invariance to complex transformations.