Summary: A generalized reaction-diffusion model of

*M. A. Cohen* and

*S. Grossberg* [see IEEE Trans. Syst. Man. Cybern. 13, 815–826 (1983;

Zbl 0553.92009)] neural networks with time-varying and distributed delays is investigated. By employing analytic methods, inequality techniques and

$M$-matrix theory, some sufficient conditions ensuring the existence, uniqueness and global exponential stability of equilibrium points for Cohen-Grossberg neural networks with time-varying and distributed delays are obtained. Several examples are given to show the effectiveness of the obtained results.