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

Eigenstructure bidirectional associative memory: an effective synthesis procedure.

G G Yen1

  • 1Structures and Controls Div., US Air Force Phillips Lab., Kirtland AFB, NM.

IEEE Transactions on Neural Networks
|January 1, 1995
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

Ranked centroid projection: a data visualization approach with self-organizing maps.

IEEE transactions on neural networks·2008
Same author

A sorting system for hierarchical grading of diabetic fundus images: a preliminary study.

IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society·2008
Same author

An effective neuro-fuzzy paradigm for machinery condition health monitoring.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
Same author

Constructing a fuzzy rule-based system using the ILFN network and Genetic Algorithm.

International journal of neural systems·2001
Same author

Winner take all experts network for sensor validation.

ISA transactions·2001
Same author

Pattern classification by a neurofuzzy network: application to vibration monitoring.

ISA transactions·2000
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 developed an efficient synthesis method for bidirectional associative memories (BAMs). This approach allows control over spurious states, estimation of memory basins, and storing more memories than the network

Area of Science:

  • Computational neuroscience
  • Artificial neural networks
  • Control systems engineering

Background:

  • Bidirectional associative memories (BAMs) are neural networks used for associative learning.
  • Existing synthesis procedures can be computationally intensive and lack control over network properties.
  • Understanding and controlling spurious states and memory capacity is crucial for BAM applications.

Purpose of the Study:

  • To propose a computationally efficient synthesis procedure for bidirectional associative memories (BAMs).
  • To provide methods for controlling spurious states and estimating basins of attraction.
  • To demonstrate the ability to store a large number of stable memories exceeding the network's order.

Main Methods:

  • Describing BAM networks using first-order ordinary difference equations on a state-space hypercube.

Related Experiment Videos

  • Developing an algorithm that extends solutions to the hypercube's corners.
  • Analyzing network properties including spurious states and stable memory capacity.

    • Main Results:

    • The proposed algorithm offers control over the number of spurious states.
    • It enables estimation of the basins of attraction for stable memories.
    • The method allows storing significantly more stable memories than the network's order under specific constraints.

    Conclusions:

    • The computationally efficient synthesis procedure enhances the utility of bidirectional associative memories.
    • The developed methods provide greater control and predictability in BAM network design.
    • The approach is applicable to real-world problems such as reconfigurable control of flexible structures.