TY - JOUR
AU1 - Nagamani, G.
AU2 - Soundararajan, G.
AU3 - Subramaniam, Ramasamy
AU4 - Azeem, Muhammad
AB - This paper is concerned with the problem of extended dissipativity analysis for delayed uncertain discrete-time singular neural networks (DTSNNs) having Markovian jump parameters and stochastic behavior. This paper demands to derive delay-dependent sufficient conditions such that the DTSNNs to be regular and causal, and is to find the stability nature and the robustness of the performance measures in the mean square sense. Based on Lyapunov–Krasovskii functional method and Cauchy–Schwartz-based summation inequality technique, a sufficient condition to guarantee an extended dissipativity performance and stability criterion for uncertain stochastic DTSNNs is presented in terms of linear matrix inequalities. Finally, numerical examples are provided to illustrate the advantages and improvements of the proposed method. Keywords Extended dissipativity analysis  Lyapunov–Krasovskii functional  Linear matrix inequality  Markovian jump parameters  Singular neural networks 1 Introduction dynamical behavior of the NNs. For this reason, many researchers have studied the stability criteria of the avail- Artificial neural networks (NNs) are the synthetic com- able NNs [1, 3, 29]. In practice, the discrete-time NNs are puting model resembling the features and structure of more applicable to problems that are inherently temporal or biological NNs. In the past few decades, NNs have gained related to biological 
TI - Robust extended dissipativity analysis for Markovian jump discrete-time delayed stochastic singular neural networks
JF - Neural Computing and Applications
DO - 10.1007/s00521-019-04497-y
DA - 2019-09-18
UR - https://www.deepdyve.com/lp/springer-journals/robust-extended-dissipativity-analysis-for-markovian-jump-discrete-Dq0J7VVr1v
SP - 1
EP - 14
VL - OnlineFirst
IS - 
DP - DeepDyve
ER -