Stability analysis and synthesis algorithm of bidirectional associative memory

Author

Yen, Gary G.

Author_Institution

USAF Philips Lab., Kirtland AFB, NM, USA

fYear

1994

fDate

13-16 Apr 1994

Firstpage

507

Abstract

Investigates the qualitative properties of 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 boundary of the hypercube. For the present model, a systematic analysis method is developed to completely characterize a given network, i.e., the distribution of equilibria in the state space, and the stability properties of the equilibrium points. In addition, the authors establish a computationally efficient synthesis procedure utilizing the eigenstructure decomposition method. The applicability of the present results is demonstrated by means of a specific application in flexible structures

Keywords

aerospace control; content-addressable storage; difference equations; eigenvalues and eigenfunctions; hypercube networks; learning (artificial intelligence); matrix algebra; recurrent neural nets; stability; bidirectional associative memory; closed hypercube; computationally efficient synthesis procedure; distribution of equilibria; eigenstructure decomposition method; equilibrium points; first order ordinary difference equations; flexible structures; qualitative properties; stability properties; state space; synthesis algorithm; systematic analysis method; Associative memory; Equations; Hypercubes; Magnesium compounds; Network synthesis; Neural networks; Neurons; Stability analysis; State-space methods; Structural engineering;

fLanguage

English

Publisher

ieee

Conference_Titel

Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on

Print_ISBN

0-7803-1865-X

Type

conf

DOI

10.1109/SIPNN.1994.344863

Filename

344863