Back to Search
Start Over
A study on state estimation for discrete-time recurrent neural networks with leakage delay and time-varying delay.
- Source :
- Advances in Difference Equations; 9/7/2016, Vol. 2016 Issue 1, p1-18, 18p
- Publication Year :
- 2016
-
Abstract
- We investigate state estimation for a class of discrete-time recurrent neural networks with leakage delay and time-varying delay. The design method for the state estimator to estimate the neuron states through available output measurements is given. A novel delay-dependent sufficient condition is obtained for the existence of state estimator such that the estimation error system is globally asymptotically stable. Based a novel double summation inequality and reciprocally convex approach, an improved stability criterion is obtained for the error-state system. Two numerical examples are given to demonstrate the effectiveness of the proposed design methods. The simulation results show that the leakage delay has a destabilizing influence on a neural network system. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 16871839
- Volume :
- 2016
- Issue :
- 1
- Database :
- Complementary Index
- Journal :
- Advances in Difference Equations
- Publication Type :
- Academic Journal
- Accession number :
- 117921958
- Full Text :
- https://doi.org/10.1186/s13662-016-0958-4