Reachable set estimation for inertial Markov jump BAM neural network with partially unknown transition rates and bounded disturbances

Ji, Huihui; He, Z. Y.; Tian, Senping

doi:10.1016/j.jfranklin.2017.08.048

Cited by 23 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BAM neural network is a two-layer neural network which can generalize not only auto-associative memory, but also hetero-associative memory [10][11][12][13][14][15][16]. This has been widely applied in many fields, such as image processing, pattern recognition, automatic control, and optimization problems.…”

Section: Introductionmentioning

confidence: 99%

Robust Stability of Fractional Order Memristive BAM Neural Networks with Mixed and Additive Time Varying Delays

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Robust Stability of Fractional Order Memristive BAM Neural Networks with Mixed and Additive Time Varying Delays

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Representatively, the global asymptotical stability problem related to inertial Cohen-Grossberg neural networks with Markov jumping parameters was studied in [19]. The issue of reachable set estimation of INNs with bounded disturbance inputs via the Markov jump model was addressed in [20]. However, it is worth mentioning that transition rates are constant due to the probability density function of sojourn time should obey the exponential distribution, in which the sojourn time stands for the interval of two consecutive jumps.…”

Section: Introductionmentioning

confidence: 99%

Finite-Time $\mathcal {L}_{2}$-$\mathcal {L}_{\infty }$ Synchronization for Semi-Markov Jump Inertial Neural Networks Using Sampled Data

Wang

Shen

et al. 2021

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

This paper investigates the finite-time synchronization issue for semi-Markov jump inertial neural networks, in which the sampled-data control is employed to alleviate the burden of the limited communication bandwidth. Due to the existence of inertial item, the semi-Markov jump inertial neural networks as hybrid neural systems, are depicted with secondorder derivatives for the first time, which can be turned to firstorder derivatives by the variable transformation. Furthermore, by applying appropriate integral inequalities and constructing the proper Lyapunov functional, some sufficient conditions, which not only guarantee the finite-time synchronization of the resulting error system but also ensure a specified level of L2-L∞ performance, are acquired based on the optimization of integral inequality technique. A numerical example is, eventually, proposed to substantiate the validity of the developed method.

show abstract

“…The signals are transmitted between neurons of X‐layer and Y‐layer, but there is no signal transmission between the neurons in the same layer. Due to its wide applications in control systems, image processing, voice processing, and many other fields, the dynamical behaviors of BAMNNs have been extensively discussed by many scholars …”

Section: Introductionmentioning

confidence: 99%

“…Due to its wide applications in control systems, image processing, voice processing, and many other fields, the dynamical behaviors of BAMNNs have been extensively discussed by many scholars. [2][3][4][5][6][7][8][9][10][11][12] As the fourth basic components besides resistor, capacitor, and inductor, the first presented by Chua 13 and made by HP Laboratory 14 provide a good hardware foundation for the development of artificial neural networks because of its distinct properties, such as low energy consumption, memory ability (hysteresis loop characteristics), and nanometer size. Memristors can replace the traditional resistors and capacitors to serve as biological synapses to transmit signals among neurons in the brain-like neural computer.…”

mentioning

confidence: 99%

Finite‐time synchronization for memristor‐based BAM neural networks with stochastic perturbations and time‐varying delays

Zhang

Peng

et al. 2018

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

Summary This paper focuses on the finite‐time synchronization issue of drive‐response memristor‐based bidirectional associative memory neural networks (MBAMNNs) with stochastic perturbations and time‐varying delays. Based on the mathematical model of memristor, definition of finite‐time stability for stochastic differential system and the drive‐response concept, some novel sufficient conditions are given to ensure the finite‐time synchronization of drive‐response MBAMNNs with stochastic perturbations and time‐varying delays. We design novel nonlinear feedback controllers to control the synchronization error to converge zero in a finite time, and the settling time for synchronization can be easily obtained. In addition, as two special cases, the finite‐time synchronization control criteria for bidirectional associative memory neural networks with stochastic perturbations and time‐varying delays and MBAMNNs without stochastic perturbations are also given. Finally, two numerical simulations are showed to demonstrate the correctness of main results.

show abstract

Reachable set estimation for inertial Markov jump BAM neural network with partially unknown transition rates and bounded disturbances

Cited by 23 publications

References 33 publications

Robust Stability of Fractional Order Memristive BAM Neural Networks with Mixed and Additive Time Varying Delays

Robust Stability of Fractional Order Memristive BAM Neural Networks with Mixed and Additive Time Varying Delays

Finite-Time $\mathcal {L}_{2}$-$\mathcal {L}_{\infty }$ Synchronization for Semi-Markov Jump Inertial Neural Networks Using Sampled Data

Finite‐time synchronization for memristor‐based BAM neural networks with stochastic perturbations and time‐varying delays

Contact Info

Product

Resources

About