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 viewpoint-invariant face representations from visual experience in an attractor network

M S Bartlett1, T J Sejnowski

  • 1University of California San Diego, Department of Cognitive Science, Salk Institute, La Jolla 92037, USA. marni@salk.edu

Network (Bristol, England)
|December 23, 1998
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

Presynaptic Vesicles Supply Membrane for Axonal Bouton Enlargement during Long Term Potentiation.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2026
Same author

Presynaptic vesicles supply membrane for axonal bouton enlargement during LTP.

bioRxiv : the preprint server for biology·2025
Same author

Stochastic self-tuning hybrid algorithm for reaction-diffusion systems.

The Journal of chemical physics·2020
Same author

A path toward understanding neurodegeneration.

Science (New York, N.Y.)·2016
Same author

Disruption of mGluR5 in parvalbumin-positive interneurons induces core features of neurodevelopmental disorders.

Molecular psychiatry·2015
Same author

Monitoring Spiking Activity of Many Individual Neurons in Invertebrate Ganglia.

Advances in experimental medicine and biology·2015
Same journal

Enhancing IoT security: A Creative Swagger Optimization algorithm for DDoS defence.

Network (Bristol, England)·2026
Same journal

Parametric optimization for electrical discharge diamond grinding (EDDG) system using dual approach.

Network (Bristol, England)·2025
Same journal

A novel lung cancer diagnosis model using hybrid convolution (2D/3D)-based adaptive DenseUnet with attention mechanism.

Network (Bristol, England)·2025
Same journal

Hybrid optimization enabled Eff-FDMNet for Parkinson's disease detection and classification in federated learning.

Network (Bristol, England)·2025
Same journal

AI-driven plant disease detection with tailored convolutional neural network.

Network (Bristol, England)·2025
Same journal

Layer modified residual Unet++ for speech enhancement using Aquila Black widow optimizer algorithm.

Network (Bristol, England)·2025
See all related articles

This study shows how networks can learn viewpoint-invariant face representations by combining Hebbian learning with temporal smoothing. This process associates temporally close visual inputs, enabling recognition across different poses.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Computer vision

Background:

  • Natural vision involves objects and faces changing viewpoints over time.
  • Developing viewpoint-invariant representations is crucial for robust object recognition.

Purpose of the Study:

  • To demonstrate how viewpoint-invariant representations of faces can emerge from visual experience.
  • To explore the role of temporal dynamics in learning these representations.

Main Methods:

  • Simulations using Hebbian learning combined with temporal smoothing of activity signals.
  • A network model with feedforward and recurrent layers, including a generalization of a Hopfield network.
  • Training on sequences of grey-level face images with changing poses.

Related Experiment Videos

Main Results:

  • Hebbian learning with temporal smoothing created an attractor network learning rule.
  • Temporally proximal input patterns were associated into basins of attraction.
  • Multiple views of the same face converged to the same basin, yielding viewpoint-invariant representations.

Conclusions:

  • The combination of Hebbian learning and temporal smoothing effectively learns viewpoint-invariant representations.
  • This approach models how biological systems might achieve robust visual recognition despite changing viewpoints.