-The problem of robust mean-square exponential stability for a class of stochastic interval cellular neural networks with time-delays is investigated. Firstly, a kind of equivalent description of this stochastic interval delayed cellular neural networks is presented. Then by using theÎto formula, Razumikhin theorems, Lyapunov function and norm inequalities, several simple sufficient conditions are obtained which guarantee the robust meansquare exponential stability of the stochastic interval cellular neural networks. and some recent results reported in the literatures are generalized.Index Terms -Robust Mean Square, Neural Networks, Timedelays. I . IntroductionIn recent years, neural networks have been extensively investigated, and successfully applied in many areas such as combinatorial optimization, signal processing, pattern recognition and many other fields. However, all successful applications are greatly dependent on the dynamic behaviors of neural networks. As is well-known now, stability is one of the main properties of neural networks, which is a crucial feature in the design of neural networks. On the other hand, axonal signal transmission delays often occur in various neural networks, and may cause undesirable dynamic network behaviors such as oscillation and instability. Up to now, the stability analysis problem of neural networks with time-delay has been attracted a large amount of research interest and many sufficient conditions have been proposed to guarantee the asymptotic or exponential stability for the neural networks with various type of time delays such as constant, timevarying, or distributed. see for example [2], [4], [12][13][14][15][16][17][18][19][20] and [24], and the references therein.Though the theoretical research on neural network has made great progress since it was born, but in many networks, such as in electronic neural networks, time delay can not be avoided. In fact, the stochastic perturbations can not be avoided either [6,7,10,11,12,21] . On the other hand, the system is unavoidable uncertainty, which is due to the existence of modeling errors, can also destroy the stability of the neural networks. So it is very important to discuss the stability and robustness of cellular network against such error and fluctuation [8,12,14] .To overcome this difficulty, we will discuss the stability problem for a kind of stochastic interval cellular neural networks with time-delays (SICNND), and derive several exponential stability criteria for the cellular neural networks(SICNND). This paper is organized as follows. In section 2, model description of the stochastic interval cellular neural networks with time-delays (SICNND), nomenclatures and lemma are given. In section 3, a kind of equivalent description of this stochastic interval delayed cellular neural networks and the idea for mean-square exponential stability are presented, and a set of some sufficient conditions is derived for the exponential stability of the stochastic interval cellular neural networks system. Finally, th...