Stability analysis of delayed Hopfield Neural Networks with impulses via inequality techniques

Pinning Synchronization of Directed Coupled Reaction-Diffusion Neural Networks With Sampled-Data Communications

This paper focuses on the design of a pinning sampled-data control mechanism for the exponential synchronization of directed coupled reaction-diffusion neural networks (CRDNNs) with sampled-data communications (SDCs). A new Lyapunov-Krasovskii functional (LKF) with some sampled-instant-dependent terms is presented, which can fully utilize the actual sampling information. Then, an inequality is first proposed, which effectively relaxes the restrictions of the positive definiteness of the constructed LKF. Based on the LKF and the inequality, sufficient conditions are derived to exponentially synchronize the directed CRDNNs with SDCs. The desired pinning sampled-data control gain is precisely obtained by solving some linear matrix inequalities (LMIs). Moreover, a less conservative exponential synchronization criterion is also established for directed coupled neural networks with SDCs. Finally, simulation results are provided to verify the effectiveness and merits of the theoretical results.

Exponential Stability Analysis for Delayed Semi-Markovian Recurrent Neural Networks: A Homogeneous Polynomial Approach

This paper investigates the exponential stability analysis issue for a class of delayed recurrent neural networks (RNNs) with semi-Markovian parameters. By constructing a stochastic Lyapunov functional and using some zoom techniques to estimate its weak infinitesimal operator, the exponential mean square stability criteria have been proposed for the Markovian neural networks with certain transition probabilities. We then generalize the homogeneous polynomial approach for the delayed Markovian RNNs with uncertain transition probabilities during the stability analysis. Theoretical results have obtained by introducing an appropriate technique for dealing with a large number of complex homogeneous polynomial matrix inequalities. Finally, numerical examples are provided to demonstrate the effectiveness of the proposed technique.

Stability of Singular Discrete-Time Neural Networks With State-Dependent Coefficients and Run-to-Run Control Strategies

In this brief, sustaining and intermittent run-to-run controllers are designed to achieve the stability of singular discrete-time neural networks with state-dependent coefficients. The controllers are designed for two reasons: 1) it is very difficult and almost impossible to only measure the in situ feedback information for the controllers and 2) the controllers may not always exist at any time. The stability is then established for singular discrete-time neural networks with state-dependent coefficients. Finally, numerical simulations are shown to illustrate the usefulness of the obtained criteria.