IEEE Transactions on Neural Networks · 2011 · 359 citations · 42 references
EngineeringMathematicsDynamical SystemsStochastic ModelingStochastic ProcessesMarkov ChainsMarkov ProcessesNeural NetworksStochastic ControlStochastic NetworksStochastic Systems ModelingDelay-dependent StabilityDiscrete DelaysDistributed Time DelaysLyapunov ControlLyapunov FunctionsPassivityPassivity TheoryTransition Probabilities
The neural networks feature finite piecewise homogeneous Markov chains and mixed delays comprising discrete and distributed components. The study conducts passivity analysis of discrete‑time stochastic neural networks with Markovian jumps and mixed delays, including scenarios with partially unknown transition probabilities. A delay‑dependent passivity condition is derived using a Lyapunov functional and linear matrix inequality techniques that account for the mixed delays. The derived passivity conditions depend on both discrete and distributed delays, and a numerical example demonstrates the methods’ effectiveness.
In this paper, passivity analysis is conducted for discrete-time stochastic neural networks with both Markovian jumping parameters and mixed time delays. The mixed time delays consist of both discrete and distributed delays. The Markov chain in the underlying neural networks is finite piecewise homogeneous. By introducing a Lyapunov functional that accounts for the mixed time delays, a delay-dependent passivity condition is derived in terms of the linear matrix inequality approach. The case of Markov chain with partially unknown transition probabilities is also considered. All the results presented depend upon not only discrete delay but also distributed delay. A numerical example is included to demonstrate the effectiveness of the proposed methods.
42