Global Convergence Analysis of Delayed Bidirectional Associative Memory Neural Networks

Author

Samli, Ruya ; Arik, Sabri

Author_Institution

Dept. of Comput. Eng., Istanbul Univ.

fYear

2006

fDate

4-7 Dec. 2006

Firstpage

313

Lastpage

316

Abstract

This paper studies the stability properties of a more general class of bidirectional associative memory (BAM) neural networks with constant time delays. Without assuming the symmetry of the interconnection matrices, and monotonicity and differentiability of the activation functions, we derive a new sufficient condition for the global asymptotic stability of the equilibrium point for bidirectional associative memory neural networks. The obtained results are independently of the delay parameters and can be easily verified. The results are also compared with the previous results derived in the literature

Keywords

asymptotic stability; content-addressable storage; neural chips; activation functions; constant time delays; delay parameters; delayed bidirectional associative memory neural networks; equilibrium point; global asymptotic stability; global convergence analysis; interconnection matrices; stability properties; Associative memory; Asymptotic stability; Computer networks; Convergence; Delay effects; Differential equations; Magnesium compounds; Neural networks; Neurons; Sufficient conditions;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2006. APCCAS 2006. IEEE Asia Pacific Conference on

Conference_Location

Singapore

Print_ISBN

1-4244-0387-1

Type

conf

DOI

10.1109/APCCAS.2006.342414

Filename

4145394