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

Autoassociative memory design using interconnected generalized brain-state-in-a-box neural networks.

Cheolhwan Oh1, Stanislaw H Zak, Guisheng Zhai

  • 1School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA. oh2@ecn.purdue.edu

International Journal of Neural Systems
|July 14, 2005
PubMed
Summary

This study introduces novel interconnected generalized Brain-State-in-a-Box (gBSB) neural networks for enhanced associative memory. The proposed design ensures stability and stronger interconnections using linear matrix inequalities (LMIs).

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

Finite-time stability analysis and control of stochastic SIR epidemic model: A study of COVID-19.

Biomedical signal processing and control·2023
Same author

VODCA: Verification of Diagnosis Using CAM-Based Approach for Explainable Process Monitoring.

Sensors (Basel, Switzerland)·2020
Same author

Stability and Stabilization in Probability of Probabilistic Boolean Networks.

IEEE transactions on neural networks and learning systems·2020
Same author

Variable neural adaptive robust control: a switched system approach.

IEEE transactions on neural networks and learning systems·2015
Same author

Correcting hypothalamic-pituitary-adrenal axis dysfunction using observer-based explicit nonlinear model predictive control.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2015
Same author

Large-scale pattern storage and retrieval using generalized brain-state-in-a-box neural networks.

IEEE transactions on neural networks·2010

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Neural Network Architectures

Background:

  • Generalized Brain-State-in-a-Box (gBSB) neural networks offer a framework for modeling complex systems.
  • Interconnecting neural subnetworks can lead to more sophisticated computational capabilities.
  • Ensuring the stability of interconnected neural networks is crucial for reliable performance.

Purpose of the Study:

  • To propose novel architectures for interconnected generalized Brain-State-in-a-Box (gBSB) neural networks.
  • To establish conditions for the stability of these proposed architectures.
  • To apply these interconnected networks for constructing neural associative memories.

Main Methods:

  • The design of interconnected gBSB neural networks is formulated as a problem of solving linear matrix inequalities (LMIs).

Related Experiment Videos

  • A novel method for solving LMIs is developed, aiming for solutions that yield stronger interconnections.
  • The proposed architectures are utilized to build and simulate neural associative memories.

    • Main Results:

    • The study successfully proposes interconnected gBSB neural network architectures with defined stability conditions.
    • A new method for solving LMIs provides solutions leading to stronger interconnections compared to standard toolboxes.
    • Simulations demonstrate the effectiveness of the proposed architectures in constructing neural associative memories.

    Conclusions:

    • Interconnected gBSB neural networks can be designed and stabilized using LMIs.
    • The developed LMI-solving method enhances interconnection strength, potentially improving associative memory performance.
    • The proposed approach offers a viable method for creating robust neural associative memories.