Global Mean Square Exponential Synchronization Of Stochastic Neural Networks With Time-varying Delays

Due to the need of artificial intelligence and the development of Internet technology,neural network,as an intelligent system which simulated human brain neural network learning,information processing and adaptive functions,has became a hot research field on Dynamics nature in recent years.Based on neural network with certainty model,random neural network added random changes,jumped out of the restrain of local optimal,and the practical application of some uncontrollable Taking random interference factors into consideration,which makes the system more close to actual.Random neural network has been widely used in optimization,risk control,intelligent control,pattern recognition and analysis of complex systems,and other fields,so for the research on random neural network on dynamic nature in theory and in fact is very meaningful.In this article,we studied the global mean square exponential synchronization of stochastic delay neural network(MSDNN).Two kinds of control scheme(that is,the state feedback controllers and output feedback controller)to stabilize a class of stochastic delay neural networks are used.By using the method of lyapunov function and it? formula,several stability conditions based on the structure of the system is established.In order to validate the results,at the last,the paper puts forward some effectiveness of the numerical simulation to prove the conclusion.The first chapter is the introduction,summarizes the characteristics,advantages and application fields and disciplines of random neural network,this paper introduces the research background and significance,research status at home and abroad and the main content of this article research.The second chapter is prepare knowledge,first of all,the basic concept of associated with this article,two assumptions and model of drive system and response system are described,and then gives the definition of error system,introduces the global mean square exponential stability and the definition of the global mean square exponential synchronization.The third chapter studies the random global mean square exponential synchronization of a class of linear neural network.The state feedback controllers and output feedback controller is designed to the two types of feedback controller stable random neural network in this paper,through the ITO formula selection and lyapunov function,make the drive system and response system to achieve global mean square exponential synchronization,and the numerical simulation is given to demonstrate the effectiveness of the conclusion.The fourth chapter is the summary and prospect,summarized the work of this paper is,and discussed on the basis of this can continue to explore some of the problems.