Mean square exponential stability of hybrid neural networks with uncertain switching probabilities

Authors:
Xuyang Lou;Qian Ye;Ke Lou;Baotong Cui
Affiliations:
Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China;Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China;Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China;Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China
Venue:
ICIC'12 Proceedings of the 8th international conference on Intelligent Computing Theories and Applications
Year:
2012

Citing 7
Cited 0

Results concerning the absolute stability of delayed neural networks

Neural Networks
Stability analysis for discrete delayed Markovian jumping neural networks with partly unknown transition probabilities

Neurocomputing
A New Sufficient Condition for Global Robust Stability of Delayed Neural Networks

Neural Processing Letters
Stochastic Exponential Stability for Markovian Jumping BAM Neural Networks With Time-Varying Delays

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Brief On robust stabilization of Markovian jump systems with uncertain switching probabilities

Automatica (Journal of IFAC)
Markovian architectural bias of recurrent neural networks

IEEE Transactions on Neural Networks
Global Robust Stability Criteria for Interval Delayed Full-Range Cellular Neural Networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper is concerned with the global exponential stability problem for a class of Markovian jumping recurrent neural networks (MJRNNs) with uncertain switching probabilities. The Markovian jumping recurrent neural networks under consideration involve parameter uncertainties in the mode transition rate matrix. By employing a Lyapunov functional, a linear matrix inequality (LMI) approach is developed to establish an easy-totest and delay-independent sufficient condition which guarantees that the dynamics of the neural network is globally exponentially stable in the mean square.