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

Restoring partly occluded patterns: a neural network model.

Kunihiko Fukushima1

  • 1School of Media Science, Tokyo University of Technology, 1404-1 Katakura, Hachioji, Tokyo 192-0982, Japan. fukushima@media.teu.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|January 15, 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

Efficient IntVec: High recognition rate with reduced computational cost.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

Introduction.

International journal of neural systems·2018
Same author

Margined winner-take-all: New learning rule for pattern recognition.

Neural networks : the official journal of the International Neural Network Society·2017
Same author

Training multi-layered neural network neocognitron.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

Artificial vision by multi-layered neural networks: neocognitron and its advances.

Neural networks : the official journal of the International Neural Network Society·2012
Same author

Increasing robustness against background noise: visual pattern recognition by a neocognitron.

Neural networks : the official journal of the International Neural Network Society·2011
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 introduces a neural network model capable of restoring occluded patterns by utilizing both bottom-up and top-down signals. The model reconstructs missing parts using learned memories and even interpolates unlearned patterns.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Computer Vision

Background:

  • Pattern recognition is challenged by occlusions.
  • Neural networks offer potential for complex data processing.
  • Hierarchical models enable multi-stage information processing.

Purpose of the Study:

  • To develop a neural network model for restoring occluded patterns.
  • To investigate the role of top-down and bottom-up signals in pattern completion.
  • To enable reconstruction of both learned and unlearned, potentially deformed, patterns.

Main Methods:

  • A multi-layered hierarchical neural network architecture was proposed.
  • Visual information processing involved interaction between bottom-up and top-down signals.

Related Experiment Videos

  • Pattern memories were stored in synaptic connections between network cells.

    • Main Results:

    • The model successfully reconstructed missing portions of partly occluded patterns.
    • Top-down signals were crucial for reconstructing occluded segments.
    • The network demonstrated restoration capabilities even for deformed or unlearned patterns.

    Conclusions:

    • The proposed neural network effectively restores occluded patterns.
    • Interaction of hierarchical signal processing enables robust pattern completion.
    • The model generalizes restoration to novel and distorted patterns.