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

Learning invariant object recognition in the visual system with continuous transformations.

S M Stringer1, G Perry, E T Rolls

  • 1Centre for Computational Neuroscience, Department of Experimental Psychology, Oxford University, South Parks Road, Oxford OX1 3UD, England.

Biological Cybernetics
|December 22, 2005
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

Brain mechanisms for invariant visual recognition and learning.

Behavioural processes·2014
Same author

Taste and olfactory status in a gourmand with a right amygdala lesion.

Neurocase·2013
Same author

Taste, olfactory and food texture reward processing in the brain and obesity.

International journal of obesity (2005)·2010
Same author

Continuous transformation learning of translation invariant representations.

Experimental brain research·2010
Same author

Differential effects on self-stimulation and motor behaviour produced by microintracranial injections of a dopamine-receptor blocking agent.

Neuroscience letters·2009
Same author

Functions of the orbitofrontal and pregenual cingulate cortex in taste, olfaction, appetite and emotion.

Acta physiologica Hungarica·2008
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

Spatial continuity aids the brain in creating invariant object representations. A new "continuous transformation learning" method leverages this spatial continuity for self-organization, offering an alternative to temporal learning.

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Computer Vision

Background:

  • The cerebral cortex uses spatiotemporal continuity to build invariant representations, crucial for object recognition in vision.
  • Existing methods, like trace learning, utilize temporal continuity for invariant object representation, but spatial continuity's role is less explored.

Purpose of the Study:

  • To investigate how spatial continuity can be used to self-organize invariant representations in a computational model.
  • To introduce and evaluate a novel learning paradigm called "continuous transformation learning".

Main Methods:

  • Developed a "continuous transformation learning" paradigm mapping spatially similar inputs to the same postsynaptic neurons.
  • Employed a competitive learning system where synapses are modified as inputs undergo continuous transformations (e.g., translation, rotation).

Related Experiment Videos

  • Utilized a hierarchical model of cortical processing in the ventral visual system.

    • Main Results:

    • Demonstrated that continuous transformation learning facilitates the self-organization of invariant representations by leveraging spatial similarity.
    • Showed that overlapping transforms of stimuli activate common postsynaptic neurons, enhancing learning.
    • Highlighted differences between continuous transformation learning and trace learning in acquiring invariant representations.

    Conclusions:

    • Spatial continuity offers a viable basis for self-organizing invariant representations in artificial systems.
    • Continuous transformation learning provides a novel mechanism for neural systems to achieve representational invariance.
    • This approach offers an alternative to temporal continuity-based learning for building robust object representations.