Wang Xue-Zhong, Wei Yimin, Stanimirović Predrag S
School of Mathematical Sciences, Fudan University, Shanghai, 200433, P.R.C.
School of Mathematical Sciences and Key Laboratory of Mathematics for Nonlinear Sciences, Fudan University, Shanghai, 200433, P.R.C.
Neural Comput. 2016 Dec;28(12):2790-2824. doi: 10.1162/NECO_a_00866. Epub 2016 Jul 8.
Two complex Zhang neural network (ZNN) models for computing the Drazin inverse of arbitrary time-varying complex square matrix are presented. The design of these neural networks is based on corresponding matrix-valued error functions arising from the limit representations of the Drazin inverse. Two types of activation functions, appropriate for handling complex matrices, are exploited to develop each of these networks. Theoretical results of convergence analysis are presented to show the desirable properties of the proposed complex-valued ZNN models. Numerical results further demonstrate the effectiveness of the proposed models.
提出了两种用于计算任意时变复方阵的Drazin逆的复值张神经网络（ZNN）模型。这些神经网络的设计基于由Drazin逆的极限表示产生的相应矩阵值误差函数。利用两种适用于处理复矩阵的激活函数来开发每个网络。给出了收敛性分析的理论结果，以展示所提出的复值ZNN模型的理想特性。数值结果进一步证明了所提模型的有效性。
