Abstract: Mean square exponential stability of Cohen-Grossberg neural networks with time-varying delays and distributed time delays is analyzed. By using differential formula and Lyapunov functional, a new delay-independent sufficient condition for exponential stability is derived. By Itoˆ differential formula, the stochastic derivative of Lyapunov functional along the considered neural network is obtained. Finally, a numerical example is given to demonstrate the usefulness of the proposed stability criteria. To the best of our knowledge, there are few results about the mean square exponential stability analysis of Cohen-Grossberg neural networks with time-varying delays and distributed time delays. Due to the representation of Cohen-Grossberg neural networks, it is significant to study its exponential stability.