Multiperiodicity of Discrete-Time Delayed Neural Networks Evoked by Periodic External Inputs

Author

Zhigang Zeng ; Jun Wang

Author_Institution

Sch. of Autom., Wuhan Univ. ofTechrology, Hubei

Volume

17

Issue

5

fYear

2006

Firstpage

1141

Lastpage

1151

Abstract

In this paper, the multiperiodicity of a general class of discrete-time delayed neural networks (DTDNNs) is formulated and studied. Several sufficient conditions are obtained to ensure n-neuron DTDNNs can have 2ⁿ periodic orbits and these periodic orbits are locally attractive. In addition, we give the conditions for a periodic orbit to be locally or globally attractive when the periodic orbit locates in a designated region. As two typical representatives, the Hopfield neural network and the cellular neural network are examined in detail. These conditions improve and extend the existing stability results in the literature. Simulations results are also discussed in three illustrative examples

Keywords

Hopfield neural nets; cellular neural nets; delay systems; discrete time systems; stability; time-varying systems; Hopfield neural network; cellular neural network; discrete-time delayed neural networks; multiperiodicity; periodic external inputs; stability; Associative memory; Automation; Cellular neural networks; Hopfield neural networks; Neural networks; Orbits; Recurrent neural networks; Stability; Sufficient conditions; Terminology; Attractivity; discrete time; induction principle; neural networks; periodic orbits; Algorithms; Artificial Intelligence; Cluster Analysis; Computing Methodologies; Models, Theoretical; Neural Networks (Computer); Oscillometry; Pattern Recognition, Automated; Periodicity; Signal Processing, Computer-Assisted;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2006.877533

Filename

1687925