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: a feature space perspective.

R Perfetti1, E Ricci

  • 1Department of Electronic and Information Engineering, University of Perugia, Perugia, Italy. perfetti@diei.unipg.it

IEEE Transactions on Neural Networks
|February 14, 2008
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

Evidence for the Collective Nature of Radial Flow in Pb+Pb Collisions with the ATLAS Detector.

Physical review letters·2026
Same author

Evidence for the Dimuon Decay of the Higgs Boson in pp Collisions with the ATLAS Detector.

Physical review letters·2025
Same author

Evidence for Longitudinally Polarized W Bosons in the Electroweak Production of Same-Sign W Boson Pairs in Association with Two Jets in pp Collisions at sqrt[s]=13  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

Observation of tt[over ¯] Production in Pb+Pb Collisions at sqrt[s_{NN}]=5.02  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

Search for Dark Matter Produced in Association with a Dark Higgs Boson in the bb[over ¯] Final State Using pp Collisions at sqrt[s]=13  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

Natural history of facioscapulohumeral muscular dystrophy evaluated by multiparametric quantitative MRI: a prospective cohort study.

Journal of neurology·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

We introduce the recurrent kernel associative memory (RKAM), a novel model that generalizes existing associative memory systems. RKAM offers improved performance and efficiency compared to prior models like ECAM and higher-order Hopfield networks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Recurrent associative memories are crucial for pattern recognition and information retrieval.
  • Existing models like RCAM, ECAM, and higher-order Hopfield networks have limitations in performance and efficiency.
  • The recent proposal of RKAM by Garcia and Moreno offers a new direction in associative memory research.

Purpose of the Study:

  • To analyze the recurrent kernel associative memory (RKAM) model.
  • To demonstrate RKAM's relationship with existing models like RCAM, ECAM, and higher-order Hopfield networks.
  • To highlight RKAM's potential for improved performance and efficiency in associative memory applications.

Main Methods:

  • Kernelization of the recurrent correlation associative memory (RCAM).

Related Experiment Videos

  • Utilizing exponential and polynomial kernels to generalize ECAM and higher-order Hopfield networks, respectively.
  • Developing a statistical measure to ascertain the dominance condition for RKAM performance.

    • Main Results:

    • RKAM is shown to be a kernelization of RCAM.
    • Using specific kernels, RKAM generalizes ECAM and higher-order Hopfield networks.
    • RKAM can outperform existing models, especially when a dominance condition is met.
    • A statistical measure for the dominance condition is proposed and validated.

    Conclusions:

    • RKAM offers a flexible and powerful framework for associative memory.
    • It provides advantages in terms of performance, dynamic range, and synaptic coefficients compared to ECAM and higher-order Hopfield networks.
    • The proposed statistical measure facilitates the practical application of RKAM.