Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Eigenstructure bidirectional associative memory: an effective synthesis procedure.

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

IEEE Transactions on Neural Networks

|January 1, 1995

Summary

This summary is machine-generated.

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

Related Experiment Videos

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

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.
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.