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

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...
Vision01:24

Vision

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.
Parallel Processing01:20

Parallel Processing

The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
Introduction to Learning01:18

Introduction to Learning

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...
Visual Agnosia01:12

Visual Agnosia

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 end"...

You might also read

Related Articles

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

Sort by
Same author

Adaptive Mixtures of Local Experts.

Neural computation·2019
Same author

Modeling natural images using gated MRFs.

IEEE transactions on pattern analysis and machine intelligence·2013
Same author

Machine learning for neuroscience.

Neural systems & circuits·2012
Same author

Comparing classification methods for longitudinal fMRI studies.

Neural computation·2010
Same author

Learning to represent spatial transformations with factored higher-order Boltzmann machines.

Neural computation·2010
Same author

Deep, narrow sigmoid belief networks are universal approximators.

Neural computation·2008
Same journal

The microlandscapes of tree trunks: the effect of lichen and tree-level characteristics on arthropod communities.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
Same journal

Centimetre-scale landscapes to assess the motion behaviour and cognition of gastropods and bivalves.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
Same journal

Intertidal microcosms of wave-swept rocky shores: ecological and physiological insights from a uniquely stressful environment.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
Same journal

Temporal and spatial variation in temperature and oxygen at the microscale: key niche axes for aquatic life.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
Same journal

Natural microcosms in ecology: fulfilling the promise of model systems?

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
Same journal

Microbe-induced galls and plant defence: metabolite crosstalk in a co-evolutionary battle.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
See all related articles

Related Experiment Video

Updated: Jun 17, 2026

Visualizing Visual Adaptation
04:43

Visualizing Visual Adaptation

Published on: April 24, 2017

Learning to represent visual input.

Geoffrey E Hinton1

  • 1Department of Computer Science, University of Toronto, Toronto, Canada. hinton@cs.toronto.edu

Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences
|December 17, 2009
PubMed
Summary
This summary is machine-generated.

Computational neuroscience models deep learning hierarchies for object recognition. New methods learn feature detectors layer-by-layer using only neural activation correlations, mimicking biological and engineering systems.

More Related Videos

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings
07:08

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Published on: August 1, 2018

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss
07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

Published on: April 11, 2025

Related Experiment Videos

Last Updated: Jun 17, 2026

Visualizing Visual Adaptation
04:43

Visualizing Visual Adaptation

Published on: April 24, 2017

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings
07:08

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Published on: August 1, 2018

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss
07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

Published on: April 11, 2025

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Artificial Intelligence

Background:

  • Understanding the cortex's object-recognition pathway and its deep hierarchy of nonlinear feature detectors is a key challenge.
  • Recent machine learning advances enable learning deep hierarchies without labeled data, focusing on generative models.

Purpose of the Study:

  • To present a novel learning procedure for deep hierarchies of feature detectors in computational neuroscience.
  • To demonstrate a method that learns without requiring labeled data, focusing on generative modeling.

Main Methods:

  • Learning feature detectors layer-by-layer using pairwise correlations between neuron-like processing units in adjacent layers.
  • Extending a quadratic energy function to include third-order, multiplicative interactions.
  • Employing a technique to factorize third-order interactions, resulting in a simplified learning rule.

Main Results:

  • The learning procedure successfully forms deep hierarchies of nonlinear feature detectors.
  • The method relies solely on pairwise correlations, simplifying the learning process.
  • The developed learning module closely resembles biologically and engineered object recognition systems.

Conclusions:

  • The proposed learning method offers a biologically plausible and computationally efficient approach to deep hierarchical learning.
  • This work bridges the gap between machine learning, computational neuroscience, and artificial intelligence in object recognition.
  • The findings suggest that simple correlation-based learning rules can underlie complex feature detection in neural systems.