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

Vision01:24

Vision

53.1K
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.
53.1K
Neuroplasticity01:01

Neuroplasticity

319
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
319
Visual System01:26

Visual System

561
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...
561

You might also read

Related Articles

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

Sort by
Same author

Deep learning for MYC binding site recognition.

Frontiers in bioinformatics·2022
Same author

Reporting of sex and gender in randomized controlled trials in Canada: a cross-sectional methods study.

Research integrity and peer review·2018
Same author

When is a randomised controlled trial health equity relevant? Development and validation of a conceptual framework.

BMJ open·2017
Same author

Interactive social media interventions to promote health equity: an overview of reviews.

Health promotion and chronic disease prevention in Canada : research, policy and practice·2016
Same author

Protocol for the development of a CONSORT-equity guideline to improve reporting of health equity in randomized trials.

Implementation science : IS·2015
Same author

Diffusion in porous building materials with high internal magnetic field gradients.

Journal of magnetic resonance (San Diego, Calif. : 1997)·2004

Related Experiment Video

Updated: Jun 17, 2025

Inducing Long-Term Plasticity of Intrinsic Neuronal Excitability in Neurons of the Dorsal Lateral Geniculate Nucleus
05:01

Inducing Long-Term Plasticity of Intrinsic Neuronal Excitability in Neurons of the Dorsal Lateral Geniculate Nucleus

Published on: September 20, 2024

348

Spontaneous Emergence of Robustness to Light Variation in CNNs With a Precortically Inspired Module.

J Petkovic1, R Fioresi2

  • 1University of Mainz, 55122 Mainz, Germany petkojan@uni-mainz.de.

Neural Computation
|August 6, 2024
PubMed
Summary
This summary is machine-generated.

Adding a preliminary convolutional module, inspired by precortical neuronal circuits, enhances the robustness of convolutional neural networks (CNNs) against light and contrast variations in image classification tasks.

More Related Videos

Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents
07:52

Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents

Published on: May 23, 2025

95
Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms
08:28

Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms

Published on: March 3, 2023

985

Related Experiment Videos

Last Updated: Jun 17, 2025

Inducing Long-Term Plasticity of Intrinsic Neuronal Excitability in Neurons of the Dorsal Lateral Geniculate Nucleus
05:01

Inducing Long-Term Plasticity of Intrinsic Neuronal Excitability in Neurons of the Dorsal Lateral Geniculate Nucleus

Published on: September 20, 2024

348
Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents
07:52

Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents

Published on: May 23, 2025

95
Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms
08:28

Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms

Published on: March 3, 2023

985

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Machine Learning

Background:

  • Analogies exist between the mammalian primary visual cortex and convolutional neural networks (CNNs) used in image classification.
  • CNNs can be sensitive to variations in global light intensity and contrast.
  • Precortical neuronal circuits offer a potential model for improving visual processing robustness.

Purpose of the Study:

  • To investigate if incorporating a preliminary convolutional module, modeled on precortical neuronal circuits, enhances CNN robustness.
  • To evaluate the impact of this module on image classification performance under varying light and contrast conditions.

Main Methods:

  • A novel preliminary convolutional module was designed based on mathematical models of precortical neuronal circuits.
  • This module was integrated into standard CNN architectures.
  • Performance was evaluated on the MNIST, FashionMNIST, and SVHN datasets under induced light intensity and contrast variations.

Main Results:

  • The addition of the precortical-inspired module significantly improved the robustness of CNNs to global light intensity variations.
  • The enhanced CNNs demonstrated greater resilience against contrast variations in input images.
  • Classification accuracy was maintained or improved across datasets despite introduced image degradations.

Conclusions:

  • A precortical-inspired convolutional module can effectively enhance the robustness of CNNs for image classification.
  • This biologically inspired approach offers a promising direction for developing more resilient computer vision systems.