Journal
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
Volume 10, Issue 4, Pages 771-785Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s13042-017-0769-2
Keywords
Discrete-time memristive neural networks; BAM neural networks; Mixed time delays; H-infinity state estimation
Categories
Funding
- King Abdulaziz University, Jeddah [RG-1-135-38]
- DSR
Ask authors/readers for more resources
In this paper, the H state estimation problem is investigated for a class of discrete-time stochastic memristive bidirectional associative memory (DSMBAM) neural networks with mixed time delays. The mixed time delays comprise both discrete and distributed time-delays. A series of novel switching functions are proposed to reflect the state-dependent characteristics of the memristive connection weights in the discrete-time setting, which facilitates the dynamics analysis of the addressed memristive neural networks (MNNs). By means of the introduced series of switching functions, an H state estimator is designed such that the estimation error is exponentially mean-square stable and the prescribed H performance requirement is achieved. The gain matrices of the desired estimator are parameterized by utilizing the semi-definite programming method. Finally, a simulation example is employed to demonstrate the usefulness and effectiveness of the proposed theoretical results.
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