Global Exponential Synchronization of Delayed Complex-Valued Recurrent Neural Networks with Discontinuous Activations

In this paper, we are concerned with the exponential synchronization for a class of two delayed complex-valued recurrent neural networks (CVRNNs) with discontinuous neuron activations. By separating CVRNNs into real and imaginary parts, forming an equivalent real-valued subsystems, under the framework of differential inclusions, novel state feedback controllers are designed and novel criteria are established to ensure the exponential stability of error system, and thus the drive system exponentially synchronize with the response system. The obtained results are essentially new and complement previously known ones. The practicability of theoretical results is also supported via a numerical example.