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

A bidirectional heteroassociative memory for binary and grey-level patterns.

Sylvain Chartier1, Mounir Boukadoum

  • 1Département de Psychologie, Université du Québec a Montréal (UQAM), Montréal, QC H3C 3P8, Canada.

IEEE Transactions on Neural Networks
|March 29, 2006
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

A bi-directional cross-channel RNN model for time-series forecasting of dairy production.

Scientific reports·2025
Same author

Fall Detection by Deep Learning-Based Bimodal Movement and Pose Sensing with Late Fusion.

Sensors (Basel, Switzerland)·2025
Same author

TinyML for Real-Time Embedded HD-EMG Hand Gesture Recognition with On-Device Fine-Tuning.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Compact Grism-Based High-resolution Colorimetric Sensing System for Liquid Samples.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

A multiscale model for multivariate time series forecasting.

Scientific reports·2025
Same author

Dynamic multilayer growth: Parallel vs. sequential approaches.

PloS one·2024
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a new bidirectional heteroassociative memory model capable of online learning and recalling grey-level patterns. This novel approach overcomes limitations of traditional bidirectional associative memories (BAM), offering improved performance and reduced complexity.

Area of Science:

  • Artificial Intelligence
  • Neural Networks
  • Machine Learning

Background:

  • Traditional bidirectional associative memories (BAM) suffer from offline learning, limited storage, noise sensitivity, and spurious states.
  • Existing BAM improvements increase complexity and cannot recall grey-level patterns.

Purpose of the Study:

  • Introduce a novel bidirectional heteroassociative memory model.
  • Enable online learning and grey-level pattern recall.

Main Methods:

  • Developed a new bidirectional heteroassociative memory model.
  • Implemented a self-convergent iterative learning rule.
  • Introduced a novel nonlinear output function.

Main Results:

Related Experiment Videos

  • The new model learns online without overlearning.
  • Demonstrated fewer spurious attractors compared to popular BAM networks.
  • Achieved comparable noise tolerance and storage capacity.
  • Enabled bidirectional learning and recall of grey-level patterns.

    • Conclusions:

    • The proposed model offers significant advantages over traditional BAMs.
    • It provides a more versatile and efficient solution for associative memory tasks.
    • The model's ability to handle grey-level patterns expands its applicability.