Uniform stability of Fractional Order Leaky Integrator Echo State Neural Network with multiple time delays

This paper deals with the uniform stability of the Fractional Order Leaky Integrator Echo State Neural Network (FOESN) with multiple delays. The delays occur in the transmission, the readout and the leakage of the network and have constant values. Sufficient conditions for uniform intrinsical stability of such networks in the presence of delays are provided. The intrinsical stability guarantees the FOESN is stable independently of the delays. In addition, the existence and uniqueness of the equilibrium point using the contraction mapping theorem are derived. Simulation results illustrate the effectiveness of the proposed method. (C) 2017 Elsevier Inc. All rights reserved.