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

Error tolerant associative memory.

C Y Liou1, S K Yuan

  • 1Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, Republic of China. cyliou@csie.ntu.edu.tw

Biological Cybernetics
|October 29, 1999
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

Shift of Sensitivity in Botrytis cinerea to Benzimidazole Fungicides in Strawberry Greenhouse Ascribing to the Rising-lowering of E198A Subpopulation and its Visual, On-site Monitoring by Loop-mediated Isothermal Amplification.

Scientific reports·2019
Same author

Assay of HIV-1 protease activity by use of crude preparations of enzyme and biotinylated substrate.

Journal of virological methods·1995
Same author

Conscious mental tasks and their EEG signals.

Medical & biological engineering & computing·1993
Same author

[Neonatal bowel perforation successfully treated by conservative treatment: report of two cases].

Zhonghua Minguo xiao er ke yi xue hui za zhi [Journal]. Zhonghua Minguo xiao er ke yi xue hui·1992
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

This study introduces a novel method to enhance associative memory capacity, improving its ability to handle noisy data and reduce errors. The new approach makes artificial memory systems more robust and efficient.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Associative memory models are crucial for understanding information storage and retrieval in biological and artificial systems.
  • Existing models often struggle with pattern completion in the presence of significant noise.
  • Enlarging the basin of attraction is key to improving memory robustness.

Purpose of the Study:

  • To develop a new training method for associative memory systems.
  • To enhance the capacity and noise tolerance of auto-associative and temporal associative memory.
  • To reduce the occurrence of spurious states (limit cycles) in trained memory networks.

Main Methods:

  • A novel training approach was developed and applied to associative memory models.

Related Experiment Videos

  • The method focuses on enlarging the basin of attraction for memory patterns.
  • Simulations were conducted to evaluate performance with noisy input patterns.

    • Main Results:

    • The proposed method significantly increases the basin of attraction for associative memory.
    • Trained memory networks demonstrate improved tolerance and recovery from severely noisy patterns.
    • A substantial reduction in the number of limit cycles was observed in simulations.

    Conclusions:

    • The new training approach offers a significant advancement in associative memory design.
    • This method enhances the reliability and performance of artificial memory systems, particularly under noisy conditions.
    • The reduction in limit cycles suggests a more stable and efficient memory representation.