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 Experiment Videos

A canonical microfunction for learning perceptual invariances

J V Stone1

  • 1Schools of Biological Sciences, University of Sussex, Falmer, Brighton, UK.

Perception
|January 1, 1996
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Where is the light? Bayesian perceptual priors for lighting direction.

Proceedings. Biological sciences·2009
Same author

Free-lunch learning: modeling spontaneous recovery of memory.

Neural computation·2006
Same author

Derivation of a clinical decision rule to guide the interhospital transfer of patients with blunt traumatic brain injury.

Emergency medicine journal : EMJ·2005
Same author

When is now? Perception of simultaneity.

Proceedings. Biological sciences·2002
Same author

Spatiotemporal independent component analysis of event-related fMRI data using skewed probability density functions.

NeuroImage·2002
Same author

Predicting spontaneous recovery of memory.

Nature·2001
Same journal

Benchmarking spatial discrimination thresholds of two-frame motion defined forms compared to luminance and stereoscopic defined forms.

Perception·2026
Same journal

The effect of face masks on the perception of trustworthiness and competence in individuals with autistic traits.

Perception·2026
Same journal

The importance of external features for categorizing ethnicity: can Koreans identify Korean, Japanese, and Chinese faces?

Perception·2026
Same journal

Interoception, alexithymia, and motor congruency: Psychological drivers of body ownership in virtual reality.

Perception·2026
Same journal

The frustration of a small <i>n</i>.

Perception·2026
Same journal

Why do we have two eyes.

Perception·2026
See all related articles

This study introduces an unsupervised learning method for neural microcircuits to extract visual information like surface depth. The approach uses a novel learning rule to maximize long-term neuron state variance, enabling generalization to new visual tasks.

Area of Science:

  • Computational Neuroscience
  • Computer Vision

Background:

  • Current methods often require supervised learning for visual tasks.
  • Extracting low-level visual features like depth is crucial for artificial intelligence.

Purpose of the Study:

  • To develop an unsupervised method for neural microcircuits to learn low-level vision tasks.
  • To demonstrate a generic strategy for learning perceptually salient visual invariances.

Main Methods:

  • An unsupervised learning approach using model neurons or microcircuits.
  • A learning rule that maximizes long-term neuron state variance while minimizing short-term variance.
  • Utilizing a combination of anti-Hebbian and Hebbian weight changes.

Main Results:

Related Experiment Videos

  • The microcircuit successfully learned to extract surface depth.
  • Demonstrated performance on a hyperacuity task: estimating subpixel stereo disparity.
  • The learned microcircuit generalized to unseen image sequences without further training.

    • Conclusions:

    • The proposed unsupervised method enables neural microcircuits to learn complex visual tasks.
    • The approach may define a canonical microfunction for learning diverse perceptual invariances.
    • This method offers a pathway for developing more adaptable artificial vision systems.