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 general model for bidirectional associative memories.

H Shi1, Y Zhao, X Zhuang

  • 1Dept. of Comput. Eng. & Comput. Sci., Missouri Univ., Columbia, MO.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|February 8, 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

Observation of the Electromagnetic Radiative Decays of the Λ(1520) and Λ(1690) to γΣ^{0}.

Physical review letters·2026
Same author

Observation of a Threshold Enhancement in the π^{+}π^{-} Spectrum in ψ(3686)→π^{+}π^{-}J/ψ Decays.

Physical review letters·2026
Same author

Phytomelatonin receptor PMTR1 is crucial for melatonin-mediated plant broad-spectrum disease resistance.

Plant cell reports·2026
Same author

Study of the Magnetic Dipole Transition of J/ψ→γη_{c} via η_{c}→pp[over ¯].

Physical review letters·2026
Same author

Observation of the Singly Cabibbo Suppressed Decay D^{0}→b_{1}(1235)^{-}e^{+}ν_{e} and Evidence for D^{+}→b_{1}(1235)^{0}e^{+}ν_{e}.

Physical review letters·2026
Same author

Unraveling the Structure of Λ Hyperons with Polarized ΛΛ[over ¯] Pairs.

Physical review letters·2025
Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015
Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
See all related articles

This study introduces a flexible model for bidirectional associative memories, enhancing pattern association without symmetrical weight constraints. It improves noisy pattern recognition and memory performance.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Bidirectional associative memories (BAMs) are neural networks for pattern association.
  • Traditional BAMs often assume symmetrical interconnection weights, limiting their applicability.
  • A need exists for more general BAM models that relax this symmetry assumption.

Purpose of the Study:

  • To propose a general model for bidirectional associative memories (GBAM) that does not require symmetrical interconnection weights.
  • To analyze the stability and learning of these general associative memories.
  • To evaluate the performance of the GBAM for noisy pattern recognition.

Main Methods:

  • Defined a supporting function to quantify state support within a GBAM.

Related Experiment Videos

  • Formulated the associative recalling process as a dynamic system.
  • Investigated stability and asymptotic stability conditions.
  • Developed a learning algorithm using the Rosenblatt perceptron rule for asymptotic stability.

    • Main Results:

    • Demonstrated the effectiveness of the GBAM for recognizing noisy patterns.
    • Showcased superior performance in terms of storage capacity, attraction, and reduced spurious memories compared to traditional models.
    • Validated the theoretical analysis through experimental results.

    Conclusions:

    • The proposed general bidirectional associative memory model offers enhanced flexibility by removing the symmetry constraint on weights.
    • The GBAM model exhibits robust performance in noisy pattern recognition and improved memory characteristics.
    • The developed learning algorithm effectively ensures asymptotic stability, making the model practical for applications.