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

Localist attractor networks.

R S Zemel1, M C Mozer

  • 1Department of Computer Science, University of Toronto, Toronto, ON M5S 1A4, Canada.

Neural Computation
|May 22, 2001
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

On the interaction of selective attention and lexical knowledge: a connectionist account of neglect dyslexia.

Journal of cognitive neuroscience·2013
Same author

The end of the line for a brain-damaged model of unilateral neglect.

Journal of cognitive neuroscience·2013
Same author

Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry.

IEEE transactions on neural networks·2008
Same author

Population coding with motion energy filters: the impact of correlations.

Neural computation·2007
Same author

Superadditive effects of multiple lesions in a connectionist architecture: implications for the neuropsychology of optic aphasia.

Psychological review·2000
Same author

Occlusion, symmetry, and object-based attention: reply to Saiki (2000).

Journal of experimental psychology. Human perception and performance·2000
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces localist attractor networks for pattern completion, offering an easier and more interpretable alternative to traditional distributed models. These networks demonstrate fewer spurious attractors and exhibit priming and gang effects.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Cognitive Science

Background:

  • Attractor networks are crucial for pattern completion, mapping input spaces to discrete outputs by cleaning noisy or incomplete data.
  • Designing distributed attractor networks is challenging due to intensive training, spurious attractors, and ill-conditioned basins, as connections encode multiple attractors.
  • The distributed nature of connections in traditional networks leads to difficulties in encoding and interpreting knowledge.

Purpose of the Study:

  • To introduce a novel formulation of attractor networks with local knowledge encoding.
  • To develop a statistical framework for localist attractor network dynamics, providing convergence proofs and parameter interpretations.
  • To evaluate the performance and properties of localist attractor networks through simulation experiments.

Related Experiment Videos

Main Methods:

  • Developed an alternative formulation of attractor networks based on local knowledge encoding.
  • Proposed a statistical model for localist attractor network dynamics.
  • Conducted simulation experiments to analyze network behavior, including attractor formation, priming, and gang effects.

Main Results:

  • Localist attractor networks are significantly easier to design, interpret, and train compared to distributed models.
  • Simulations showed that localist networks produce fewer spurious attractors.
  • These networks exhibit desirable properties like priming and gang effects, relevant to psychological and neurobiological models.

Conclusions:

  • Localist attractor networks offer a more tractable and interpretable approach to pattern completion tasks.
  • The proposed statistical formulation provides theoretical guarantees and insights into model parameters.
  • The demonstrated properties suggest the potential utility of localist attractor networks in modeling cognitive and neural processes.