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

Using Spatio-temporal Correlations to Learn Invariant Object Recognition.

Guy Wallis1

  • 1Max-Planck Institute für Biologische Kybernetik, Germany

Neural Networks : the Official Journal of the International Neural Network Society
|December 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

Schizotypy and perceptual span in a non-clinical sample: a virtual reality study.

Cognitive neuropsychiatry·2024
Same author

Express Visuomotor Responses Reflect Knowledge of Both Target Locations and Contextual Rules during Reaches of Different Amplitudes.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2023
Same author

Symbolic cues enhance express visuomotor responses in human arm muscles at the motor planning rather than the visuospatial processing stage.

Journal of neurophysiology·2022
Same author

Visual-haptic integration, action and embodiment in virtual reality.

Psychological research·2021
Same author

Trial-by-trial modulation of express visuomotor responses induced by symbolic or barely detectable cues.

Journal of neurophysiology·2021
Same author

Microsaccades and covert attention: Evidence from a continuous, divided attention task.

Journal of eye movement research·2021
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

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

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

This study introduces a competitive network using a Hebb-like learning rule for object classification. This novel approach outperforms supervised methods in invariant character recognition tasks, even with limited data.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Traditional object recognition systems often struggle with temporal and spatial data.
  • Supervised learning methods require extensive labeled datasets for effective training.
  • Existing models like Fukushima's Neocognitron have limitations in certain learning scenarios.

Purpose of the Study:

  • To develop a novel competitive network for object classification.
  • To investigate the efficacy of a Hebb-like learning rule incorporating temporal and spatial correlations.
  • To compare the performance of this new learning rule against established supervised methods.

Main Methods:

  • Implementation of a competitive neural network architecture.
  • Utilizing a Hebb-like learning rule that considers both prior and current neural activity.

Related Experiment Videos

  • Training and testing the network on invariant character recognition tasks.
  • Comparative analysis against a standard supervised learning rule and Fukushima's Neocognitron.

    • Main Results:

    • The Hebb-like learning rule demonstrated superior performance on cross-validation tests for invariant character recognition with small training sets.
    • The proposed network outperformed the supervised version of Fukushima's Neocognitron on a larger dataset.
    • The network effectively learns object classification by leveraging temporal and spatial correlations.

    Conclusions:

    • The developed Hebb-like learning rule offers a powerful alternative to supervised learning for object classification.
    • This approach shows significant potential for improving invariant character recognition, especially in data-scarce environments.
    • The findings suggest a promising direction for more efficient and effective neural network learning.