Three new ZNN models with economical dimension and exponential convergence for real-time solution of moore-penrose pseudoinverse

Zhang neural network (ZNN) is a novel class of recurrent neural network with superior solution ability and convergence performance. For real-time solution of Moore-Penrose pseudoinverses of time-varying matrices based on continuous-time recurrent neural network, this paper proposes three different ZNN models, each of which is derived from a specifically-chosen Zhang function (ZF). Theoretical analyses guarantee the global convergence of the three different ZNN models and their fast convergence rate. Besides, the proposed ZNN models show additional great advantages when used to deal with matrices with contrasting numbers of rows and columns. Computer simulations and experiments further verify the theoretical results, vividly demonstrating the effectiveness and efficiency of the proposed ZNN models.