Eigenstructure bidirectional associative memory: an effective synthesis procedure

Author

Yen, Gary G.

Author_Institution

Structures & Controls Div., US Air Force Phillips Lab., Kirtland AFB, NM, USA

Volume

6

Issue

5

fYear

1995

fDate

9/1/1995 12:00:00 AM

Firstpage

1293

Lastpage

1297

Abstract

We propose a computationally efficient synthesis procedure for a class of bidirectional associative memories. Networks are described by a system of first-order ordinary difference equations which are defined on a closed hypercube of the state-space with solutions extended to the corner of the hypercube. The proposed algorithm possesses several advantages since it is possible: 1) to exert control over the number of spurious states; 2) to estimate the basins of attraction of the stable memories; and 3) under certain constraints, to effectively store a number of desired stable memories which by far exceed the order of the network. The applicability of the present results is demonstrated by means of a specific application in reconfigurable control of flexible structures

Keywords

associative processing; content-addressable storage; difference equations; feedforward neural nets; flexible structures; hypercube networks; neurocontrollers; state-space methods; attraction basin; closed hypercube; eigenstructure bidirectional associative memory; first-order ordinary difference equations; flexible structures; incremental learning; nonlinear feedforward neural network; reconfigurable control; state-space; Algorithm design and analysis; Approximation algorithms; Associative memory; Hypercubes; Magnesium compounds; Network synthesis; Neural networks; Stability; Stochastic processes; Structural engineering;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.410378

Filename

410378