Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
411610 | Neurocomputing | 2016 | 7 Pages |
Abstract
This work studies the problem of finite-time stochastic boundedness of discrete-time Markovian jump neural networks with boundary transition probabilities and randomly varying nonlinearities. The partly unknown and uncertain transition probabilities (TPs) are included in the paper, and more general nonlinearities are introduced with both upper and lower bounds due to the nature of its probability information. By employing the free-weighting matrix technique, finite-time stability theory and boundary incomplete TPs, the solvability sufficient conditions of finite-time stochastic boundedness are given. Finally, numerical examples are presented to demonstrate the effectiveness of the proposed approach.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Liyuan Hou, Jun Cheng, Hailing Wang,