Analysis of Markovian Jump Stochastic Cohen–Grossberg BAM Neural Networks with Time Delays for Exponential Input-to-State Stability

In this article, the Input-to-state stability theory is used to investigate the stochastic Cohen–Grossberg bidirectional associative memory neural network with time-varying delay. In addition, Markovian jump parameters are considered in this model to determine the continuous-time, discrete-state Mar...

Full description

Saved in:
Bibliographic Details
Published inNeural processing letters Vol. 55; no. 8; pp. 11055 - 11072
Main Authors Radhika, T., Chandrasekar, A., Vijayakumar, V., Zhu, Quanxin
Format Journal Article
LanguageEnglish
Published New York Springer US 01.12.2023
Springer Nature B.V
Subjects
Artificial Intelligence
Associative memory
Complex Systems
Computational Intelligence
Computer Science
Equilibrium
Inequality
Markov chains
Neural networks
Neurons
Recurrent neural networks
Signal processing
Stability
Stochastic models
BAM neural networks
Input-to-state stable
Stochastic systems
Time-varying delay
Markovian jump
Online AccessGet full text

Cover

More Information
Summary:In this article, the Input-to-state stability theory is used to investigate the stochastic Cohen–Grossberg bidirectional associative memory neural network with time-varying delay. In addition, Markovian jump parameters are considered in this model to determine the continuous-time, discrete-state Markov chain. By utilizing Lyapunov functional and weak infinitesimal generator the algebraic conditions are derived for Input-to-state criteria. In the end, a numerical example is given to show the merits of the given method.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1370-4621
1573-773X
DOI:10.1007/s11063-023-11364-4