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 transform invariant object recognition in the visual system with multiple stimuli present during training.

S M Stringer1, E T Rolls

  • 1Oxford University, Centre for Computational Neuroscience, Department of Experimental Psychology, South Parks Road, Oxford OX1 3UD, England, United Kingdom. simon.stringer@psy.ox.ac.uk

Neural Networks : the Official Journal of the International Neural Network Society
|April 29, 2008
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

Preferences for medication attributes among patients with type 2 diabetes mellitus in the UK.

Diabetes, obesity & metabolism·2013
Same author

The role of independent motion in object segmentation in the ventral visual stream: Learning to recognise the separate parts of the body.

Vision research·2011
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 journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study shows that competitive neural networks can learn to recognize individual objects even when multiple objects are present in training images. This self-organization enables the development of transform-invariant representations crucial for visual processing.

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Artificial Intelligence

Background:

  • The visual system develops neurons with transform invariance for object and face recognition.
  • Existing computational models often train networks with single stimuli, limiting realism.
  • Understanding self-organization in visual models with complex stimuli is crucial.

Purpose of the Study:

  • To investigate how vision models self-organize when trained with multiple stimuli simultaneously.
  • To determine if competitive networks can learn individual stimulus representations from complex inputs.
  • To explore the development of transform-invariant representations in multi-stimulus environments.

Main Methods:

  • Utilized standard competitive neural networks and a multi-layer hierarchical model (VisNet).

Related Experiment Videos

  • Trained networks on visual stimuli presented together within single images.
  • Introduced multiple transforming objects (e.g., rotating 3D objects) during training.

    • Main Results:

    • Competitive networks spontaneously switched to representing individual stimuli as stimulus numbers increased.
    • Networks learned position and view invariant representations of individual stimuli.
    • VisNet successfully developed view-invariant representations of individual objects from complex scenes.

    Conclusions:

    • Training with multiple stimuli promotes self-organization and individual stimulus representation in neural networks.
    • This approach enables the development of transform-invariant visual representations.
    • The findings have implications for understanding biological vision and developing advanced AI systems.