A delay‐dependent asymptotic stability criteria for uncertain BAM neural networks with leakage and discrete time‐varying delays: A novel summation inequality

Abstract

This proposed research work aims to investigate the problem of uncertain BAM neural networks with leakage and discrete time‐varying delays in the sense of asymptotic stable by applying convex combination approach, discrete‐time Wirtinger inequality. It is pointed out that a novel summation inequality is entrenched based on discrete type Wirtinger based inequality. By the aid of novel inequality, reciprocally convex combination technique, time‐varying delays are examined to certify the stability of neural networks. Here, the uncertainties are considered as a randomly occurring parameter uncertainties and it conforms certain mutually uncorrelated Bernoulli‐distributed white noise sequences. The important feature of the results reported here is that the probability of occurrence of the parameter uncertainties are known a priori. To demonstrate the theoretical results of this research paper, numerical examples are given to expo the validity and efficiency of our results with the help of LMI Control toolbox in matlab.

New delay‐dependent H∞ state estimator for static neural networks with bounded and unbounded time delays

“…Notably, the results are presented in terms of delay-independent or delay-dependent. What is more, compared to the case of delay-independent, these delay-dependent conditions may appear to be less conservative and robust (see, for instance, previous studies [5][6][7][8]20,26,27]). It is well known that SNNs, which is regarded as a class of recurrent NNs, have received increasing interest due to its versatility broad.…”

“…As a comprehensive and interdisciplinary subject, neural networks (NNs) have aroused great concerns in the fields of medical expert system, face recognition, traffic flow prediction, and adaptive control [1][2][3][4][5][6][7][8][9][10]. Recently, different kinds of NN models, such as neutral-type NNs, fractional-order NNs, complex-valued NNs [11][12][13], and memristor-based NNs, have been investigated in many literatures.…”

Global exponential stability of discrete-time Hopfield neural network models with unbounded delays

“…Since the work of Golpasamy [15], the continuous neural network models with delay in the leakage terms have been studied by several authors [18,26,33] but, as far as we know, there are few results concerning the stability of discrete-time neural network models with delay in the leakage terms [6,27,28].…”

“…The problem of stability of equilibrium of discrete-time Hopfield neural network models with delays has been studied [6,10,16,22,23,27,28,31,35]. However, the models considered have finite delays [10,16,22,23,27,28,31,35], or with infinite delays but just for low-order models with discrete delays independent of the neurons [6].…”

Almost sure exponential stability of hybrid stochastic delayed Cohen–Grossberg neural networks

“…Due to the effect of numerous tanglesome factors in the real world, the stability (stabilization) issue of stochastic systems has attracted a lot of attention, particularly stochastic neural networks have become a hotly debated topic (see other studies [1][2][3][4][5][6][7]) and so forth. The Cohen-Grossberg neural network (CGNN) is a class of neural network model first raised by Cohen and Grossberg in 1983 [8] which includes population biology, neurobiology, evolutionary theory, and another famous models as its peculiar cases.…”