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 weighted voting model of associative memory.

Xiaoyan Mu1, Paul Watta, Mohamad H Hassoun

  • 1Department of Electrical and Computer Engineering, Rose-Hulman Institute of Technology, Terre Haute, IN 47803, USA. mu@Rose-Hulman.edu

IEEE Transactions on Neural Networks
|May 29, 2007
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

All-silk fibroin-based dual-drug delivery system for antibacterial and antioxidant wound repair.

International journal of biological macromolecules·2026
Same author

Molecular-weight-dependent antioxidant functions of silk fibroin fragments for engineering sustained-release composite hydrogels.

International journal of biological macromolecules·2026
Same author

Arginine Delays Postharvest Softening of Button Mushroom (<i>Agaricus bisporus</i>) via Lipid Metabolism Regulation.

Foods (Basel, Switzerland)·2025
Same author

Antioxidant activity of extracts from immobilized microalgae: Growth characteristics and active packaging application.

International journal of biological macromolecules·2025
Same author

Children's drug research and development incentives and market pricing optimization based on medical imaging.

Scientific reports·2025
Same author

Unconventional Natural Gas Charging and Enrichment Characteristics in Coal-Measure Tight Reservoirs of Southeast Ordos Basin, North China.

ACS omega·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a weighted voting associative memory using random access memory (RAM). This novel memory model demonstrates high capacity, error correction, and effective pattern retrieval with a rejection mechanism.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Information Retrieval

Background:

  • Associative memory models are crucial for information retrieval.
  • Existing models often lack robustness or a rejection mechanism.
  • Random access memory (RAM) offers potential for efficient memory implementation.

Purpose of the Study:

  • To analyze a novel random access memory (RAM)-based associative memory.
  • To evaluate a weighted voting scheme for enhanced information retrieval.
  • To assess the model's performance in heteroassociative and autoassociative modes.

Main Methods:

  • Theoretical analysis of a weighted voting memory system.
  • Derivation of performance measures based on model parameters (pattern size, window size, number of patterns).

Related Experiment Videos

  • Evaluation for binary and random memory sets, storing real-valued and binary-valued patterns.

    • Main Results:

    • The weighted voting memory exhibits large storage capacity and significant error correction capabilities.
    • High detection and identification rates were achieved.
    • Low false acceptance rates were simultaneously maintained, demonstrating model efficacy.

    Conclusions:

    • The weighted voting associative memory offers a robust and efficient solution for information retrieval.
    • The model's performance metrics indicate its suitability for complex pattern recognition tasks.
    • The integrated rejection mechanism enhances reliability in memory operations.