Reachable set estimation for discrete-time Markovian jump neural networks with unified uncertain transition probability
Files
(Published version)
Date
2023
Authors
Tian, Y.
Ao, W.
Shi, P.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Journal of Automation and Intelligence, 2023; 2(3):167-174
Statement of Responsibility
Yufeng Tian, Wengang Ao, Peng Shi
Conference Name
Abstract
This paper focuses on the reachable set estimation for Markovian jump neural networks with time delay. By allowing uncertainty in the transition probabilities, a framework unifies and enhances the generality and realism of these systems. To fully exploit the unified uncertain transition probabilities, an equivalent transformation technique is introduced as an alternative to traditional estimation methods, effectively utilizing the information of transition probabilities. Furthermore, a vector Wirtinger-based summation inequality is proposed, which captures more system information compared to existing ones. Building upon these components, a novel condition that guarantees a reachable set estimation is presented for Markovian jump neural networks with unified uncertain transition probabilities. A numerical example is illustrated to demonstrate the superiority of the approaches.
School/Discipline
Dissertation Note
Provenance
Description
Available online 9 September 2023
Access Status
Rights
© 2023 The Authors. Published by Elsevier B.V. on behalf of KeAi Communications Co. Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).