부산대학교 도서관

This paper investigates the problem of exponential stability of Neural Networks (NNs) with Markovianparameters and general noise. The model in this paper with general noise is more suitable for many real nervoussystems than NNs with white noise. Criteria for the exponential stability of the NNs with Markovian switchingparameters and general noise in both the mean square and p-th moment are derived by utilizing the random analysismethod and Lyapunov functional method techniques. The exponential stability of NNs without Markovian switchingis given as a special case. Finally, simulation result in two examples are discussed to illustrate the theoreticalresults.
This paper investigates the problem of exponential stability of Neural Networks (NNs) with Markovianparameters and general noise. The model in this paper with general noise is more suitable for many real nervoussystems than NNs with white noise. Criteria for the exponential stability of the NNs with Markovian switchingparameters and general noise in both the mean square and p-th moment are derived by utilizing the random analysismethod and Lyapunov functional method techniques. The exponential stability of NNs without Markovian switchingis given as a special case. Finally, simulation result in two examples are discussed to illustrate the theoreticalresults.