The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper is concerned with global exponential stability problem for a class of neural networks with time-varying delays. An appropriate Lyaponov-krasovskii functional (LKF) is constructed firstly. The symmetric matrices involved in the LKF are not required to be all positive definite. The obtained criterion expressed in terms of linear matrix inequalities (LMIs) shows advantages over the existing...
This paper is concerned with the problem of sampled-data filtering for delayed neural network subject to sensor saturation. Rather than the continuous measurements, the neural network measurements are sampled and then transmitted to the filter simultaneously considering sensor saturation constraints. By using the input delay approach, the sampling period is converted into a bounded time-vary delay...
In this paper, the problem of finite-time stabilization for a class of memristor-based neural networks with time-varying delays is investigated by using hybrid impulsive and nonlinear feedback controllers. Based on the theory of the differential equations with discontinuous right and Lyapunov function approach, several sufficient conditions are derived to guarantee the finite-time stabilization of...
In this paper, the exponential stochastic synchronization of coupled neural networks via adaptive periodically intermittent control is further investigated. Based on the Lyapunov stability theory combined with the method of the adaptive control, periodically intermittent control and the properties of Weiner process, some simple criteria are derived for the exponential stochastic synchronization of...
This paper investigates the synchronization problem of delayed Markovian coupled neural networks with random coupling strengths and partial information on transition probabilities. In this coupled neural network model, each transition rate is only known partial information, and the coupling strengths are characterized by mutually independent random variables. By constructing a new augmented Lyapunov-Krasovskii...
In this paper, the delay-probability-distribution-dependent stability problem for stochastic neural networks with various time-varying delays is investigated. By considering a new Lyapunov-Krasovskii functional (LKF) concluding more delay-partitioning term and combining free weight matrices and stochastic processing techniques, an improved delay-probability-distribution-dependent condition is built...
The issues of mean-square finite-time stability analysis and state estimator design for stochastic switched delayed neural networks are investigated in this paper. A stability criterion with average dwell time constraint is proposed, such that the mean-square value of state is not larger than a prescribed threshold during a given time interval. Then, a state estimator, which ensures mean-square finite-time...
We investigate the evolution of a delayed feedforward network model with plasticity. It is found that desynchronized and synchronized firing patterns both exist in the feedforward network (FFN) with different synaptic delays. Synaptic delays may play a significant role in bridging rate coding and time coding. Then we focus on the evolution of firing rate and synaptic weights in the FFN network based...
In industrial process, some important variables such as quality index, efficiency index and concentration of product components are difficult or even impossible to be measured directly due to the limitation of technology. This phenomenon leads to few labeled data and plenty of unlabeled data. Traditional identification method for controlled auto regressive (CAR) model usually cannot deal with unlabeled...
In this paper, two methods were considered to estimate the distance, which aims to study the influence of external environmental factors on localization accuracy. The first method is log-normal shadowing model (LNSM), which estimates the distance through the received signal strength indicator (RSSI). The second method is improved algorithm based on RBF neural network (RBFNN). Two different experimental...
In this paper, the global exponential stability in Lagrange sense for complex-valued neural networks with discrete time-varying delays and distributed time-varying delays is investigated. A criterion to ensure the global exponential stability in Lagrange sense for complex-valued neural networks with discrete time-varying delays and distributed time-varying delays is obtained by employing Lyapunov-Krasovskii...
Effective mechanical state prediction systems are critical to modern manufacturing systems and industries. As a method of deep learning algorithm, Recurrent neural network, (RNN) has been playing an increasingly important role in the field of time series prediction. In order to solve the problem of hard training and gradient extinction of RNN model, a long short-term memory network (LSTM) algorithm...
In this paper, we put forward deep neural network ensemble to model and predict Chinese stock market index (including Shanghai composite index and SZSE component index), based on the input indices of recent days. A set of component networks are trained by historical data for this task, where Backpropagation and Adam algorithm are used to train each network efficiently. Bagging approach combines these...
This paper presents an improved result on H∞ state estimation for static neural networks with a time-varying delay. First, a novel Lyapunov-Krasovskii functional (LKF) with several augmented terms is constructed. Then, a relaxed integral inequality is employed to make a tight estimation for single integral terms with time-varying delay in the derivative of the LKF. As a result, a delay-dependent criterion...
This paper is concerned with finite-time synchronization for two models of coupled Cohen-Grossberg neural networks with time-varying delays. In the first one, linearly coupled Cohen-Grossberg neural networks is considered. In the second one, nonlinearly coupled Cohen-Grossberg neural networks is discussed. Based on finite-time stability theory, some inequality techniques, and designed controllers,...
This paper makes a Hopf bifurcation analysis of a two-neuron network with mixed time delays. The network contains two discrete delays and two distributed delays. The sum of discrete delays is chosen as the bifurcation parameter, and the conditions of the stability and Hopf bifurcation are achieved by analyzing its characteristic equation. Finally, numerical simulations are carried out to illustrate...
In this paper, an effective optimize method based on adaptive PID neural network controller is presented. Chaotic Particle Swarm Optimization (CPSO) is introduced to initialize the parameters of neural network for improving the convergent speed and preventing weights trapping into local optima. In order to realize the hardware platform of PID neural network controller and facilitate weight update...
Aiming at the problem that the key water quality parameters in wastewater treatment processing is difficult to detect real-time accurately. An ammonia nitrogen concentration soft measure model based on the artificial neural network(ANN) is proposed in this paper, and utilizing existing data to achieve parameters detection in real-time accurately during the process of wastewater treatment processing...
This paper is focused on the asymptotical synchronization of memristor-based neural networks with time-varying delays via adaptive controllers. In existing investigations, most results about synchronization of MNNs can only be applied to some specific MNNs. Thus, we introduce a new simple adaptive controller to synchronize two MNNs with time-varying delays asymptotically. Furthermore, some new conditions...
This paper pay attention to the state estimation problem for a class of delayed neural networks with reaction-diffusion terms. By constructing a Lyapunov functional, together with the Hardy-Poincare inequality, a less conservative sufficient condition for the existence of state estimator is formulated in terms of linear matrix inequality (LMI). Finally, a numerical example is given to demonstrate...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.