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

Recurrent correlation associative memories.

T D Chiueh1, R M Goodman

  • 1Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA.

IEEE Transactions on Neural Networks
|January 1, 1991
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

Effect of Organic Amendments on Soilborne and Foliar Diseases in Field-Grown Snap Bean and Cucumber.

Plant disease·2019
Same author

In situ detection of early replication phases of a gemini virus in legume protoplasts.

Plant cell reports·2013
Same author

How to institutionalize health promotion programs.

American journal of health promotion : AJHP·2011
Same author

The life and death of a health promotion program: an institutionalization case study.

International quarterly of community health education·2010
Same author

Regression Analyses for Evaluating the Influence of Bacillus cereus on Alfalfa Yield Under Variable Disease Intensity.

Phytopathology·2008
Same author

Up-regulation of OsBIHD1, a rice gene encoding BELL homeodomain transcriptional factor, in disease resistance responses.

Plant biology (Stuttgart, Germany)·2005
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

A new model for high-capacity associative memories, called recurrent correlation associative memories (RCAMs), offers exponential storage capacity. An exponential correlation associative memory (ECAM) chip demonstrates practical application and high-speed performance.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Neuroscience

Background:

  • Associative memories are crucial for AI and cognitive modeling.
  • Existing models face limitations in storage capacity and stability.
  • Recurrent neural networks offer a promising framework for advanced memory systems.

Purpose of the Study:

  • To introduce a novel class of high-capacity associative memories based on recurrent neural networks.
  • To analyze the stability and storage capacity of these novel models.
  • To demonstrate the practical implementation and application of an advanced associative memory design.

Main Methods:

  • Development of a mathematical model for recurrent correlation associative memories (RCAMs).
  • Analysis of RCAM stability under synchronous and asynchronous update modes.

Related Experiment Videos

  • Proposal and analysis of the exponential correlation associative memory (ECAM) model.
  • Design, fabrication, and testing of a CMOS ECAM chip.

    • Main Results:

    • RCAMs exhibit asymptotic stability with continuous, monotone nondecreasing weighting functions.
    • The ECAM model achieves exponential scaling of storage capacity with pattern length, reaching theoretical limits.
    • The ECAM chip successfully stores 32 24-bit patterns with recall speeds exceeding 1 associative operation per 3 microseconds.
    • Limited dynamic range in exponentiation nodes affects capacity proportionally.

    Conclusions:

    • RCAMs, particularly the ECAM, represent a significant advancement in high-capacity associative memory design.
    • The ECAM chip validates the theoretical capacity and performance predictions.
    • The ECAM technology holds potential for applications like vector quantization.