Abstract
This paper focuses on the problem of delay-dependent robust dissipativity analysis for a class of stochastic fuzzy neural networks with time-varying delay. The randomly occurring uncertainties under consideration are assumed to follow certain mutually uncorrelated Bernoulli-distributed white noise sequences. Based on the Itô's differential formula, Lyapunov stability theory, and linear matrix inequalities techniques, several novel sufficient conditions are derived using delay partitioning approach to ensure the dissipativity of neural networks with or without time-varying parametric uncertainties. It is shown, by comparing with existing approaches, that the delay-partitioning projection approach can largely reduce the conservatism of the stability results. Numerical examples are constructed to show the effectiveness of the theoretical results.
Highlights
Over the past few decades, dynamical behavior of neural networks (NNs)has been studied much in science and technology area, such as signal processing, parallel computing,c 2019 Authors
The importance of dissipativity has been widely recognized, few results have been proposed for the dissipativity of stochastic fuzzy neural networks with time-varying delay [21]
The problem of dissipativity analysis has been investigated for stochastic fuzzy neural networks with time delay using delay partitioning approach
Summary
Over the past few decades, dynamical behavior of neural networks (NNs)has been studied much in science and technology area, such as signal processing, parallel computing,. Stability analysis of stochastic neural networks with time-delays has received much attention; see, for example, [14,41,42]. The importance of dissipativity has been widely recognized, few results have been proposed for the dissipativity of stochastic fuzzy neural networks with time-varying delay [21]. This motivates the work of this paper. We are concerned with the problem of dissipativity for stochastic fuzzy neural networks with time delay. X > 0), where X is a symmetric matrices, means that X is positive semi-definite
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
