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

Stability and attractivity in associative memory networks.

M Cottrell1

  • 1UA 743 CNRS Statistique Appliquée, Université Paris XI, Orsay, France.

Biological Cybernetics
|January 1, 1988
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

Population Pharmacokinetics Modeling of Unbound Efavirenz, Atazanavir, and Ritonavir in HIV-Infected Subjects With Aging Biomarkers.

CPT: pharmacometrics & systems pharmacology·2016
Same author

Phenotypic variations of orpk mutation and chromosomal localization of modifiers influencing kidney phenotype.

Physiological genomics·2002
Same author

A stochastic model for interconnected neurons.

Bio Systems·1997
Same author

Comments about "Analysis of the convergence properties of topology preserving neural networks".

IEEE transactions on neural networks·1995
Same author

Neural modeling for time series: A statistical stepwise method for weight elimination.

IEEE transactions on neural networks·1995
Same author

Altered platelet indices in dogs with hypothyroidism and cats with hyperthyroidism.

American journal of veterinary research·1993
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

Researchers designed a connection matrix for neuron-like networks to ensure stable and attractive states for memorized patterns. This matrix enhances pattern recall and stability in artificial neural systems.

Area of Science:

  • Computational neuroscience
  • Network theory
  • Artificial intelligence

Background:

  • Understanding stable states is crucial for neural network function.
  • Attractivity of patterns determines memory recall in neural systems.
  • Neuron-like elements form the basis of many computational models.

Purpose of the Study:

  • To determine the connection matrix for stable and attractive states in a network.
  • To guarantee the stability and strongest attractivity of p memorized patterns.
  • To analytically evaluate the attractivity of these patterns.

Main Methods:

  • Calculation of a specific connection matrix.
  • Analytical evaluation of pattern attractivity.
  • Computer simulations for result verification.

Related Experiment Videos

Main Results:

  • A connection matrix was calculated that ensures stability and strong attractivity for memorized patterns.
  • Analytical methods provided a quantitative evaluation of pattern attractivity.
  • Simulations confirmed the theoretical findings.

Conclusions:

  • The proposed connection matrix effectively stabilizes and enhances the attractivity of memorized patterns.
  • The analytical evaluation provides a framework for understanding and predicting network behavior.
  • The findings have implications for designing more robust artificial neural networks.