Exponential stabilization of delayed recurrent neural networks: A state estimation based approach. Academic Article

abstract

• This paper is concerned with the stabilization problem of delayed recurrent neural networks. As the states of neurons are usually difficult to be fully measured, a state estimation based approach is presented. First, a sufficient condition is derived such that the augmented system under consideration is globally exponentially stable. Then, by employing a decoupling technique, the gain matrices of the controller and state estimator are achieved by solving some linear matrix inequalities. Finally, a delayed neural network with chaotic behaviors is exploited to demonstrate the applicability of the developed result.

authors

• Huang, Tingwen

published proceedings

• Neural Netw

altmetric score

• 3

author list (cited authors)

• Huang, H. e., Huang, T., Chen, X., & Qian, C.

citation count

• 51

complete list of authors

• Huang, He||Huang, Tingwen||Chen, Xiaoping||Qian, Chunjiang

publication date

• December 2013

publisher

• Elsevier  Publisher

published in

• Neural Networks  Journal

keywords

• Algorithms
• Computer Simulation
• Decoupling
• Exponential Stabilization
• Linear Models
• Markov Chains
• Neural Networks, Computer
• Neurons
• Nonlinear Dynamics
• Recurrent Neural Networks
• State Estimation
• Time Delay

PubMed Central ID

• 24055957

Digital Object Identifier (DOI)

• 10.1016/j.neunet.2013.08.006

start page

• 153

end page

• 157

volume

• 48

URL

• http%3A%2F%2Fdx.doi.org%2F10.1016%2Fj.neunet.2013.08.006