In this paper, we deal with the exponential synchronization problem for a class of chaotic neural networks with mixed delays and impulsive effects via output coupling with delay feedback. The mixed delays in this paper include time-varying delays and unbounded distributed delays. by using a Lyapunov-Krasovskǐ functional, a drive-response concept and a linear matrix inequality (LMI) approach, several sufficient conditions are established that guarantee the exponential synchronization of the neural networks. Also, the estimation gains can be easily obtained. Finally, a numerical example and its simulation are given to show the effectiveness of the obtained results.