作者: Shengyuan Xu , James Lam , Daniel W.C. Ho , Yun Zou
DOI: 10.1016/J.PHYSLETA.2004.03.038
关键词: Convex optimization 、 Compact space 、 Applied mathematics 、 Physics 、 Interval (mathematics) 、 Bounded function 、 Exponential stability 、 Equilibrium point 、 Linear matrix inequality 、 Recurrent neural network
摘要: This Letter investigates the problem of robust global exponential stability analysis for interval recurrent neural networks (RNNs) via linear matrix inequality (LMI) approach. The values time-invariant uncertain parameters are assumed to be bounded within given compact sets. An improved condition existence a unique equilibrium point and its RNNs with known is proposed. Based on this, sufficient obtained. Both conditions expressed in terms LMIs, which can checked easily by various recently developed convex optimization algorithms. Examples provided demonstrate reduced conservatism proposed condition.