Journal
NEUROCOMPUTING
Volume 168, Issue -, Pages 1111-1120Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2015.05.012
Keywords
Memristor; Recurrent neural network; Non-fragile control; Random fluctuation; Different memductance function
Categories
Funding
- NBHM/DAE [2/48(8)/2014/NBHM (R.P)/RD II/954]
- Department of Science and Technology, Government of India, New Delhi [DST/INSPIRE Fellowship/2011- IF110718]
Ask authors/readers for more resources
In this paper, we discussed non-fragile state estimation problem for a class of memristive neural networks with two different types of memductance functions and uncertain time-varying delays. The required results are derived by using a suitable Lyapunov-Krasovskii functional (LKF) and using linear matrix inequality (LMI) approach together with Wirtinger-type inequality analysis. The sufficient conditions are presented for the existence of non-fragile state estimator based on the combined H-infinity and passivity performance criterions. The results are proposed in terms of LMIs, which can guarantee the global asymptotic stability of the error dynamics between the considered memristive RNNs and its non-fragile observer. Finally, a numerical example is presented to illustrate the effectiveness of the theoretical results via simulations. (C) 2015 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available