Sliding Mode Control-Based Synchronization of Complex-Valued Neural Networks

Synchronization is a typical dynamical behaviour of interconnected systems that is being extensively studied in neural networks. However, most of the research considers real-valued neural networks, and less results have been obtained on their complex-valued counterparts. This work presents two sliding mode control strategies to achieve synchronization in a complex-valued neural network. The former simplifies an already existing technique that splits the control into real and imaginary parts. The latter extends a fully complex-valued sliding approach for generic complex-valued dynamical systems to the multi-input multi-output case, and shows its efficiency and higher performance in terms of finite reaching time in the synchronization of complex-valued neural networks. The approach is validated via numerical simulations.