On impulsive autoassociative neural networks

Multiagent Meta-Reinforcement Learning for Adaptive Multipath Routing Optimization

In this article, we investigate the routing problem of packet networks through multiagent reinforcement learning (RL), which is a very challenging topic in distributed and autonomous networked systems. In specific, the routing problem is modeled as a networked multiagent partially observable Markov decision process (MDP). Since the MDP of a network node is not only affected by its neighboring nodes' policies but also the network traffic demand, it becomes a multitask learning problem. Inspired by recent success of RL and metalearning, we propose two novel model-free multiagent RL algorithms, named multiagent proximal policy optimization (MAPPO) and multiagent metaproximal policy optimization (meta-MAPPO), to optimize the network performances under fixed and time-varying traffic demand, respectively. A practicable distributed implementation framework is designed based on the separability of exploration and exploitation in training MAPPO. Compared with the existing routing optimization policies, our simulation results demonstrate the excellent performances of the proposed algorithms.

Multistability of Delayed Hybrid Impulsive Neural Networks With Application to Associative Memories

The important topic of multistability of continuous-and discrete-time neural network (NN) models has been investigated rather extensively. Concerning the design of associative memories, multistability of delayed hybrid NNs is studied in this paper with an emphasis on the impulse effects. Arising from the spiking phenomenon in biological networks, impulsive NNs provide an efficient model for synaptic interconnections among neurons. Using state-space decomposition, the coexistence of multiple equilibria of hybrid impulsive NNs is analyzed. Multistability criteria are then established regrading delayed hybrid impulsive neurodynamics, for which both the impulse effects on the convergence rate and the basins of attraction of the equilibria are discussed. Illustrative examples are given to verify the theoretical results and demonstrate an application to the design of associative memories. It is shown by an experimental example that delayed hybrid impulsive NNs have the advantages of high storage capacity and high fault tolerance when used for associative memories.

Dynamic Analysis of Hybrid Impulsive Delayed Neural Networks With Uncertainties

Neural networks (NNs) have emerged as a powerful illustrative diagram for the brain. Unveiling the mechanism of neural-dynamic evolution is one of the crucial steps toward understanding how the brain works and evolves. Inspired by the universal existence of impulses in many real systems, this paper formulates a type of hybrid NNs (HNNs) with impulses, time delays, and interval uncertainties, and studies its global dynamic evolution by a robust interval analysis. The HNNs incorporate both continuous-time implementation and impulsive jump in mutual activations, where time delays and interval uncertainties are represented simultaneously. By constructing a Banach contraction mapping, the existence and uniqueness of the equilibrium of the HNN model are proved and analyzed in detail. Based on nonsmooth Lyapunov functions and delayed impulsive differential equations, new criteria are derived for ensuring the global robust exponential stability of the HNNs. Convergence analysis together with illustrative examples show the effectiveness of the theoretical results.

Effects of variable-time impulses on global exponential stability of Cohen–Grossberg neural networks

We investigate the global exponential stability of Cohen–Grossberg neural networks (CGNNs) with variable moments of impulses using B-equivalence method. Under certain conditions, we show that each solution of the considered system intersects each surface of discontinuity exactly once, and that the variable-time impulsive systems can be reduced to the fixed-time impulsive ones. The obtained results imply that impulsive CGNN will remain stability property of continuous subsystem even if the impulses are of somewhat destabilizing, and that stabilizing impulses can stabilize the unstable continuous subsystem at its equilibrium points. Moreover, two stability criteria for the considered CGNN by use of proposed comparison system are obtained. Finally, the theoretical results are illustrated by two examples.

Hybrid impulsive and switching Hopfield neural networks with state-dependent impulses

We discuss the global stability of switching Hopfield neural networks (HNN) with state-dependent impulses using B-equivalence method. Under certain conditions, we show that the state-dependent impulsive switching systems can be reduced to the fixed-time ones, and that the global stability of corresponding comparison system implies the same stability of the considered system. On this basis, a novel stability criterion for the considered HNN is established. Finally, two numerical examples are given to demonstrate the effectiveness of our results.

PERIODICITY AND STABILITY IN RECURRENT CELLULAR NEURAL NETWORKS WITH IMPULSIVE EFFECTS

In this paper, the exponential stability analysis problem is considered for a class of impulsive recurrent cellular neural networks (IRCNNs) with time-varying delays. Without assuming the boundedness on the activation functions, some sufficient conditions are derived for checking the existence and exponential stability of periodic solution for this system by using Mawhin's continuation theorem of coincidence degree theory and constructing suitable Lyapunov functional. It is believed that these results are significant and useful for the design and applications of IRCNNs. Finally, an example with numerical simulation is given to show the effectiveness of the proposed method and results.

GLOBAL EXPONENTIAL STABILITY OF FUZZY INTERVAL DELAYED NEURAL NETWORKS WITH IMPULSES ON TIME SCALES

In this paper, we investigate the existence and uniqueness of equilibrium point for fuzzy interval delayed neural networks with impulses on time scales. And we give the criteria of the global exponential stability of the unique equilibrium point for the neural networks under consideration using Lyapunov method. Finally, we present an example to illustrate that our results are effective.

Impulsive control of stochastic systems with applications in chaos control, chaos synchronization, and neural networks

Real systems are often subject to both noise perturbations and impulsive effects. In this paper, we study the stability and stabilization of systems with both noise perturbations and impulsive effects. In other words, we generalize the impulsive control theory from the deterministic case to the stochastic case. The method is based on extending the comparison method to the stochastic case. The method presented in this paper is general and easy to apply. Theoretical results on both stability in the pth mean and stability with disturbance attenuation are derived. To show the effectiveness of the basic theory, we apply it to the impulsive control and synchronization of chaotic systems with noise perturbations, and to the stability of impulsive stochastic neural networks. Several numerical examples are also presented to verify the theoretical results.

Stationary oscillation for chaotic shunting inhibitory cellular neural networks with impulses

In this paper, we study stationary oscillation for general shunting inhibitory cellular neural networks with impulses which are complex nonlinear neural networks. In a recent paper [Z. J. Gui and W. G. Ge, Chaos 16, 033116 (2006)], the authors claimed that they obtained a criterion of existence, uniqueness, and global exponential stability of periodic solution (i.e., stationary oscillation) for shunting inhibitory cellular neural networks with impulses. We point out in this paper that the main result of their paper is incorrect, and presents a sufficient condition of ensuring existence, uniqueness, and global stability of periodic solution for general shunting inhibitory cellular neural networks with impulses. The result is derived by using a new method which is different from those of previous literature. An illustrative example is given to demonstrate the effectiveness.

Impulsive Effects on Stability of Fuzzy Cohen–Grossberg Neural Networks With Time-Varying Delays

In this correspondence, the impulsive effects on the stability of fuzzy Cohen-Grossberg neural networks (FCGNNs) with time-varying delays are considered. Several sufficient conditions are obtained ensuring global exponential stability of equilibrium point for the neural networks by the idea of vector Lyapunov function, M-matrix theory, and analytic methods. Moreover, the estimation for exponential convergence rate index is proposed. The obtained results not only show that the stability still remains under certain impulsive perturbations for the continuous stable FCGNNs with time-varying delays, but also present an approach to stabilize the unstable FCGNNs with time-varying delays by utilizing impulsive effects. An example with simulations is given to show the effectiveness of the obtained results.

Global exponential stability of impulsive high-order BAM neural networks with time-varying delays

In this paper, global exponential stability and exponential convergence are studied for a class of impulsive high-order bidirectional associative memory (BAM) neural networks with time-varying delays. By employing linear matrix inequalities (LMIs) and differential inequalities with delays and impulses, several sufficient conditions are obtained for ensuring the system to be globally exponentially stable. Three illustrative examples are also given at the end of this paper to show the effectiveness of our results.

Exponential Stability of Impulsive High-Order Hopfield-Type Neural Networks With Time-Varying Delays

This paper considers the problems of global exponential stability and exponential convergence rate for impulsive high-order Hopfield-type neural networks with time-varying delays. By using the method of Lyapunov functions, some sufficient conditions for ensuring global exponential stability of these networks are derived, and the estimated exponential convergence rate is also obtained. As an illustration, an numerical example is worked out using the results obtained.