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 robust method for distinguishing between learned and spurious attractors.

Anthony V Robins1, Simon J R McCallum

  • 1Department of Computer Science, The University of Otago, P.O. Box 56, Dunedin 9015, New Zealand. anthony@cs.otago.ac.nz

Neural Networks : the Official Journal of the International Neural Network Society
|March 24, 2004
PubMed
Summary

This study introduces a new energy profile method to distinguish between learned and spurious states in Hopfield networks. This robust technique aids in understanding network behavior and recall processes.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

Injecting reasoning into vision-language models via weight-decomposed merging.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Non-equilibrium thermodynamic framework for neural networks: A principled correspondence and parameter dynamics.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dual-pathway mask ranking guided selective fine-tuning for backdoor purification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Discriminative transfer feature learning for unsupervised domain adaptation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

ARetinex-Net: Low-light image enhancement with adaptive retinex model and global illumination representation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Multi-Task Learning Framework with Physics Embedded for Signal Reconstruction and State Prediction in Underground Multi-Robot Systems.

Neural networks : the official journal of the International Neural Network Society·2026

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Cognitive Science

Background:

  • Hopfield networks and constraint satisfaction models can autoassociate patterns.
  • Network inputs may converge to learned or spurious (unlearned) states.
  • Distinguishing between learned and spurious states is crucial for network analysis.

Purpose of the Study:

  • To present a robust and general method for distinguishing learned from spurious states in Hopfield networks.
  • To enhance the understanding of pattern recall and recognition in artificial neural networks.
  • To explore connections between computational models and psychological concepts of familiarity.

Main Methods:

  • Development of a novel 'energy profile' method.
  • Application of the method to analyze network states.

Related Experiment Videos

  • Comparison with existing approaches and related psychological literature.

    • Main Results:

    • The energy profile method reliably distinguishes between learned and spurious states.
    • Demonstration of the method's robustness and generalizability.
    • Identification of links to psychological concepts of recall and familiarity.

    Conclusions:

    • The energy profile method offers a significant advancement in analyzing Hopfield network dynamics.
    • This approach provides a valuable tool for researchers in computational neuroscience and AI.
    • Findings suggest potential applications in understanding human memory and recognition processes.