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

State-dependent weights for neural associative memories

R Kothari1, R Lotlikar, M Cahay

  • 1Department of Electrical and Computer Engineering and Computer Science, University of Cincinnati, OH 45221-0030, USA.

Neural Computation
|March 21, 1998
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

Particle composition and morphology over urban environment (New Delhi): Plausible effects on wheat leaves.

Environmental research·2021
Same author

Recurrent erythema nodosum leprosum associated with Mycobacterium indicus pranii vaccine in a case of leprosy: a rare paradox.

Journal of the European Academy of Dermatology and Venereology : JEADV·2021
Same author

Use of polypropylene mesh in contaminated and dirty strangulated hernias: short-term results.

Hernia : the journal of hernias and abdominal wall surgery·2018
Same author

Rechallenge temozolomide in glioma: A case series from India.

Indian journal of cancer·2017
Same author

Patterns of care and outcomes for second-line targeted therapy in metastatic renal cell carcinomas: A registry based analysis.

Indian journal of cancer·2017
Same author

Phycoremediation of textile wastewater by unicellular microalga Chlorella pyrenoidosa.

Cellular and molecular biology (Noisy-le-Grand, France)·2014
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 enhances neural associative memory performance by dynamically adjusting the weight matrix. A novel method optimizes a constant (eta) for improved memory recall, even with unknown noise levels.

Area of Science:

  • Computational neuroscience
  • Artificial intelligence
  • Machine learning

Background:

  • Neural associative memories (NAMs) are crucial for pattern recognition and information retrieval.
  • Traditional NAMs face performance limitations due to fixed weight matrices, especially in noisy environments.
  • Dynamic weight modification offers a potential solution to improve NAM robustness and capacity.

Purpose of the Study:

  • To investigate the impact of dynamically modifying the weight matrix on neural associative memory performance.
  • To analytically derive the optimal parameter for dynamic weight adjustment.
  • To validate the proposed method through experimental analysis under various conditions.

Main Methods:

  • Implementing dynamic weight modification by adding scaled outer products of current states to the correlation weight matrix.

Related Experiment Videos

  • Analytically determining the optimal scaling constant (eta) for single-shot synchronous dynamics.
  • Conducting experimental evaluations for both synchronous and asynchronous updating dynamics.

    • Main Results:

    • An analytical method was developed to find the optimal value of eta for dynamic weight modification.
    • The optimal eta value improves neural associative memory performance, particularly in the presence of noise.
    • Effective performance was demonstrated even when the exact noise percentage was unknown.
    • The method's efficacy was confirmed for asynchronous updating with a transient length greater than 1.

    Conclusions:

    • Dynamically modifying the weight matrix is an effective strategy for enhancing neural associative memory performance.
    • The proposed method, involving the optimization of eta, offers a robust approach to improve memory recall.
    • This technique shows promise for applications requiring reliable pattern recognition in the presence of data imperfections.