Dynamics Analysis Of Two Types Of Parameter Mismatched Memristive Neural Networks

Artificial neural network is a kind of mathematical model which imitates the structure and function of biological neural network.This kind of network depends on the complexity of the system and adjusts the relationship between a large number of nodes.As two kinds of special neural networks,coupled neural network can better describe the characteristics of biological complex neurons,while the potential application of memristive neural network in the next generation of human brain computer,so they have attracted many scholars' attention in recent years.This paper mainly investigates the synchronization and quasi-synchronization of delayed fractional coupled memristive neural networks with parameter mismatch,as well as the problem of H? state estimation of delayed recurrent memristive neural networks with both continuous-time and discrete-time cases.The main works are as follows:1.The synchronization and quasi-synchronization of delayed fractional coupled memristive neural networks with parameter mismatch are investigated.A criterion is first provided to guarantee the asymptotic synchronization of the master and slave systems by designing a discontinuous controller and constructing a Lyapunov functional.Meanwhile,a quasi-synchronization criterion for the underlying systems is also derived.The given conditions can be easily checked by solving linear matrix inequalities,the correctness of our theoretical analysis are demonstrated by two numerical examples.2.The problem of H? state estimation of delayed recurrent memristive neural networks with both continuous-time and discrete-time cases are studied.By utilizing Lyapunov functional and linear matrix inequalities,two criterions are provided to guarantee the asymptotically stable of the estimation error systems with a H?performance.The connection weight parameters of DRMNNs are dealed with logical switching signals,which greatly reduces the computational complexity.The given conditions can be easily checked by solving linear matrix inequalities,the correctness of our theoretical analysis are demonstrated by two numerical examples.