Impulsive controller design for exponential synchronization of delayed stochastic memristor-based recurrent neural networks

Chandrasekar, A.; Rakkiyappan, R.

doi:10.1016/j.neucom.2015.08.088

Cited by 82 publications

(27 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show that this self-organizing recurrent neural network can obtain a low architectural complexity and good generalization performance. Other related results can be found in [46]- [47].…”

Section: Introductionsupporting

confidence: 55%

Self-organization of a recurrent RBF neural network using an information-oriented algorithm

2017

View full text Add to dashboard Cite

This paper investigates how to construct a recurrent radial basis function neural network (RRBFNN) by an information-oriented algorithm (IOA) and how to adjust the parameters by a gradient algorithm simultaneously. In this IOA-based RRBFNN (IOA-RRBFNN), the proposed IOA is used to calculate the information processing strength (IPS) of hidden neurons, such that the independent component contributions between the hidden neurons and output neurons can be extracted. Then, a novel self-organizing strategy is proposed to optimize the structure of RRBFNN based on the input IPS and output IPS of hidden neurons. Meanwhile, a gradient algorithm is developed to update the parameters of IOA-RRBFNN. The proposed IOA-RRBFNN can be used to organize the network structure and adjust the parameters to improve its performance. Finally, several examples are presented to illustrate the effectiveness of IOA-RRBFNN. The results demonstrate that the proposed IOA-RRBFNN is more competitive in solving the nonlinear system modeling problems compared with some existing methods. Index Terms-Information-oriented algorithm; recurrent radial basis function neural network; information processing strength; component contributions.

show abstract

Section: Introductionsupporting

confidence: 55%

Self-organization of a recurrent RBF neural network using an information-oriented algorithm

2017

View full text Add to dashboard Cite

show abstract

“…and obviously, * = 0 is an equilibrium point of the sliding mode dynamics (37). On account of the sliding mode control theory, a reaching law is denoted as = − (sgn ( ( ))) ,…”

Section: Resultsmentioning

confidence: 99%

“…In fact, functions and parameters of master-slave system are often mismatched, which is inevitable. Although various forms of control strategies have been designed to solve the problems of system's synchronization [25,27,30,[37][38][39][40], they are difficult to deal with projective synchronization of NFMNN. In order to solve such problems, the fractionalorder sliding mode controller is introduced, which can overcome the uncertainty of systems and has strong robustness to disturbance, especially for the control of nonlinear systems.…”

Section: Introductionmentioning

confidence: 99%

Projective Synchronization of Nonidentical Fractional-Order Memristive Neural Networks

Chen

Ding

2019

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

This paper investigates projective synchronization of nonidentical fractional-order memristive neural networks (NFMNN) via sliding mode controller. Firstly, based on the sliding mode control theory, a new fractional-order integral sliding mode controller is designed to ensure the occurrence of sliding motion. Furthermore, according to fractional-order differential inequalities and fractional-order Lyapunov direct method, the trajectories of the system converge to the sliding mode surface to carry out sliding mode motion, and some sufficient criteria are obtained to achieve global projective synchronization of NFMNN. In addition, the conclusions extend and improve some previous works on the synchronization of fractional-order memristive neural networks (FMNN). Finally, a simulation example is given to verify the effectiveness and correctness of the obtained results.

show abstract

“…Besides, it only requires small control gains and acts at certain discrete instants, thereby reducing the amount of transmitted information and control costs [14]. Considering the advantages of the impulsive control strategy, the issue of impulsive synchronization of MNNs has been wildly studied [15][16][17][18][19]. In [15], by utilizing the distributed impulsive control method, the synchronization problem for a class of MNNs with stochastic disturbance has been extensively studied.…”

Section: Introductionmentioning

confidence: 99%

Event-triggered hybrid impulsive control for synchronization of memristive neural networks

Zhang

Bao

2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

This paper is concerned with the complete synchronization of memristive neural networks (MNNs) with time-varying delays. An event-triggered hybrid state feedback and impulsive controller is designed to save the limited system communication resources, and parameter mismatch is considered in the control design process. Based on the Lyapunov functional approach and the comparison principle for impulsive systems, a sufficient synchronization criterion is developed to derive the master MNN and response MNN. Additionally, under the event-triggered mechanism there exists a positive lower bound for inter-execution time, which implies the avoidance of Zeno behavior. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed synchronization design methods.

show abstract

Impulsive controller design for exponential synchronization of delayed stochastic memristor-based recurrent neural networks

Cited by 82 publications

References 30 publications

Self-organization of a recurrent RBF neural network using an information-oriented algorithm

Self-organization of a recurrent RBF neural network using an information-oriented algorithm

Projective Synchronization of Nonidentical Fractional-Order Memristive Neural Networks

Event-triggered hybrid impulsive control for synchronization of memristive neural networks

Contact Info

Product

Resources

About