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

Nested-Clique Network Model of Neural Associative Memory.

Asieh Abolpour Mofrad1, Matthew G Parker2

  • 1Selmer Center, Department of Informatics, University of Bergen, Bergen 5020, Norway Asieh.Mofrad@uib.no.

Neural Computation
|April 15, 2017
PubMed
Summary

Researchers enhanced neural associative memories using nested-clique graph structures. This novel approach improves performance in clique-based models, offering better learning capacity and retrieval rates for complex data patterns.

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

Association Between Use of Any of the Drugs Prescribed in Norway and the Subsequent Risk of Parkinson Disease: A Drug-wide Association Study.

Neurology·2023
Same author

Computational models of stimulus equivalence: An intersection for the study of symbolic behavior.

Journal of the experimental analysis of behavior·2023
Same author

On Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournaments.

Neural computation·2021
Same author

Balanced difficulty task finder: an adaptive recommendation method for learning tasks based on the concept of state of flow.

Cognitive neurodynamics·2020
Same author

Equivalence Projective Simulation as a Framework for Modeling Formation of Stimulus Equivalence Classes.

Neural computation·2020
Same author

Clique-Based Neural Associative Memories with Local Coding and Precoding.

Neural computation·2016

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Graph Theory

Background:

  • Clique-based neural associative memories (GB model) demonstrate effective performance.
  • Previous work enhanced GB models using local coding and precoding for partial erasures.

Purpose of the Study:

  • To investigate the impact of nested-clique graph structures on clique-based neural associative memories.
  • To improve learning capacity and retrieval rates beyond previous enhancements.

Main Methods:

  • Implementation of nested-clique graph structures within the GB model framework.
  • Comparative simulations evaluating performance against standard clique-based models.

Main Results:

  • The nested-clique structure significantly enhances the performance of the clique-based neural associative memory model.

Related Experiment Videos

  • Improved learning capacity and retrieval rates were observed with the new structure.

    • Conclusions:

    • Nested-clique graph structures represent a significant advancement for clique-based neural associative memories.
    • This topology offers superior performance for pattern storage and retrieval in neural networks.