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

Convolution Properties II01:17

Convolution Properties II

594
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
594
Convolution Properties I01:20

Convolution Properties I

621
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
621
Protein Networks02:26

Protein Networks

4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
Protein Networks02:26

Protein Networks

2.9K
2.9K
Network Covalent Solids02:18

Network Covalent Solids

16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

972
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
972

You might also read

Related Articles

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

Sort by
Same author

Human-aligned evaluation of a pixel-wise DNN color constancy model.

Frontiers in human neuroscience·2026
Same author

Human gloss perception reproduced by tiny neural networks.

Nature human behaviour·2026
Same author

Swiping colors in virtual reality: How stable are color category borders?

Journal of vision·2026
Same author

A deep convolutional neural network trained for lightness constancy is susceptible to lightness illusions.

Journal of vision·2026
Same author

Deep neural networks trained for estimating reflectance and illumination achieve lightness constancy differently than human observers.

Journal of vision·2026
Same author

Keeping your eye, head, and hand on the ball: Rapidly orchestrated visuomotor behavior in a continuous action task.

Journal of vision·2025

Related Experiment Video

Updated: Feb 12, 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

1.1K

Processing of chromatic information in a deep convolutional neural network.

Alban Flachot, Karl R Gegenfurtner

    Journal of the Optical Society of America. A, Optics, Image Science, and Vision
    |April 1, 2018
    PubMed
    Summary

    Deep neural networks like AlexNet process color information in early layers similarly to the primate brain, using decorrelated linear features for efficient representation. Higher layers show reduced color sensitivity, mirroring early visual system processing.

    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

    10.0K
    Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
    06:19

    Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

    Published on: August 16, 2024

    884

    Related Experiment Videos

    Last Updated: Feb 12, 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

    1.1K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.0K
    Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
    06:19

    Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

    Published on: August 16, 2024

    884

    Area of Science:

    • Computer Science
    • Neuroscience
    • Artificial Intelligence

    Background:

    • Deep convolutional neural networks (CNNs) demonstrate human-like performance in tasks like object recognition.
    • Understanding the internal computations of CNNs and their parallels with the primate brain remains a significant challenge.

    Purpose of the Study:

    • To investigate how color information is processed across different layers of the AlexNet deep neural network.
    • To compare the color processing mechanisms learned by AlexNet with those found in the primate visual system.

    Main Methods:

    • Analysis of color-responsive units in various layers of AlexNet, a CNN trained on object classification.
    • Comparison of learned feature representations and tuning properties with known primate visual system functions.

    Main Results:

    • Early layers of AlexNet exhibit color-responsive units learning linear features, broadly tuned to two decorrelated directions in color space, analogous to primate thalamus cells.
    • Chromatic and achromatic information are segregated in early network layers, similar to the primate visual system.
    • Higher layers of AlexNet show decreased responsivity to color compared to earlier layers.

    Conclusions:

    • AlexNet's early layers develop color processing strategies that share similarities with early stages of the primate visual system.
    • The findings suggest that deep learning models may learn biologically plausible mechanisms for visual information processing.