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

Associative memory design using support vector machines.

Daniele Casali1, Giovanni Costantini, Renzo Perfetti

  • 1Department of Electronic Engineering, University of Rome "Tor Vergata," 00100 Rome, Italy. daniele.casali@uniroma2.it

IEEE Transactions on Neural Networks
|September 28, 2006
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

Artificial Intelligence in Healthcare and Public Health: Emerging Applications, Clinical Integration and Future Directions.

Bioengineering (Basel, Switzerland)·2026
Same author

Ultra-narrow donor-acceptor nanoribbons.

Nature communications·2026
Same author

Focused ultrasound thalamotomy improves voice tremor in essential tremor: objective insight from artificial intelligence.

Scientific reports·2026
Same author

Revealing the Full Potential of Glycolated Mixed Ionic-Electronic Semiconductors - Symmetric Monomer Polymerization to Boost Electrochemical Transistor Performance.

Journal of the American Chemical Society·2026
Same author

Vocabulary-Free Image Classification and Semantic Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

L-Dopa Comparably Improves Gait and Limb Movements in Parkinson's Disease: A Wearable Sensor Analysis.

Biomedicines·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 explores the link between Support Vector Machines (SVMs) and recurrent associative memories. SVMs offer an efficient method for designing these neural networks, revealing a generalized Hebb

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Artificial intelligence

Background:

  • Recurrent associative memories are crucial for cognitive functions.
  • Designing these memories often involves complex neural network models.
  • Generalized Brain-State-in-a-Box (GBSB) offers a framework for neural modeling.

Purpose of the Study:

  • To investigate the relationship between Support Vector Machines (SVMs) and recurrent associative memories.
  • To formulate the design of GBSB-based associative memories using SVMs.
  • To evaluate the performance of this SVM-based approach.

Main Methods:

  • Formulating the design of GBSB neural networks as independent classification tasks.
  • Utilizing standard Support Vector Machine (SVM) learning software.

Related Experiment Videos

  • Comparing the SVM approach with existing methods using nonsymmetric connections.

    • Main Results:

    • The design of GBSB associative memories can be efficiently solved using SVMs.
    • Networks designed via SVMs exhibit properties like a generalized Hebb's law.
    • The SVM approach demonstrates competitive performance compared to existing methods.

    Conclusions:

    • Support Vector Machines provide an effective tool for designing recurrent associative memories.
    • The SVM-based design method simplifies the creation of GBSB neural networks.
    • This approach offers a novel and efficient way to implement associative memory systems.