Finite time anti-synchronization of complex-valued neural networks with bounded asynchronous time-varying delays

The finite time anti-synchronization of master-slave coupled complex-valued neural networks (CVNNs) with bounded asynchronous time-varying delays is studied. With the decomposing technique and generalized {xi, infinity}-norm, several criteria for ensuring the finite time anti-synchronization are obtained. The whole anti-synchronized process is divided into two phases (it is called Two-Phases-Method, 2PM): first, the norm of each error state component will flow from initial value to 1 in finite time, then flow from 1 to 0 also in finite time, thus the whole processing time is finite. Finally, a numerical example is presented to demonstrate the effectiveness of our obtained results. (C) 2020 Elsevier B.V. All rights reserved.