Improved Zhang neural network model and its solution of time-varying generalized linear matrix equations

In this paper, a class of Zhang neural networks (ZNNs) are developed and analyzed on convergence properties. Different from conventional gradient-based neural networks (GNNs), such ZNN is designed based on the idea of measuring the time-derivation information of time-varying coefficients. The general framework of such a ZNN, together with its variant forms, is presented and investigated. The resultant ZNN model activated by linear functions possesses global exponential convergence to the time-varying equilibrium point. By employing proposed new smooth nonlinear odd-monotonically increasing activation functions, superior convergence could be achieved. Computer-simulation examples substantiate the efficacy of such a ZNN model in the context of solution of time-varying generalized linear matrix equations.

[1]  Yau-Hwang Kuo,et al.  Hardware implementation of CMAC neural network with reduced storage requirement , 1997, IEEE Trans. Neural Networks.

[2]  Jun Wang,et al.  Global exponential stability of recurrent neural networks for synthesizing linear feedback control systems via pole assignment , 2002, IEEE Trans. Neural Networks.

[3]  Wei Wu,et al.  Deterministic convergence of an online gradient method for BP neural networks , 2005, IEEE Transactions on Neural Networks.

[4]  Hiroomi Hikawa,et al.  A digital hardware pulse-mode neuron with piecewise linear activation function , 2003, IEEE Trans. Neural Networks.

[5]  Shuzhi Sam Ge,et al.  Design and analysis of a general recurrent neural network model for time-varying matrix inversion , 2005, IEEE Transactions on Neural Networks.

[6]  S. Himavathi,et al.  Feedforward Neural Network Implementation in FPGA Using Layer Multiplexing for Effective Resource Utilization , 2007, IEEE Transactions on Neural Networks.

[7]  Jian-Da Wu,et al.  An automotive generator fault diagnosis system using discrete wavelet transform and artificial neural network , 2009, Expert Syst. Appl..

[8]  Feng Ding,et al.  Gradient Based Iterative Algorithms for Solving a Class of Matrix Equations , 2005, IEEE Trans. Autom. Control..

[9]  Murat Sari,et al.  Predicting effect of physical factors on tibial motion using artificial neural networks , 2009, Expert Syst. Appl..

[10]  Ke Chen,et al.  Zhang Neural Network Versus Gradient Neural Network for Online Time-Varying Quadratic Function Minimization , 2008, ICIC.

[11]  Binghuang Cai,et al.  Zhang neural network without using time-derivative information for constant and time-varying matrix inversion , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[12]  Shuzhi Sam Ge,et al.  A unified quadratic-programming-based dynamical system approach to joint torque optimization of physically constrained redundant manipulators , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Yu-Nong Zhang,et al.  Zhang Neural Network for Linear Time-Varying Equation Solving and its Robotic Application , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[14]  Ke Chen,et al.  MATLAB Simulation and Comparison of Zhang Neural Network and Gradient Neural Network for Time-Varying Lyapunov Equation Solving , 2008, ISNN.

[15]  R. Mulholland,et al.  Kronecker product representation for the solution of the general linear matrix equation , 1980 .

[16]  Yunong Zhang,et al.  Revisit the Analog Computer and Gradient-Based Neural System for Matrix Inversion , 2005, Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation Intelligent Control, 2005..

[17]  Ke Chen,et al.  MATLAB Simulation of Gradient-Based Neural Network for Online Matrix Inversion , 2009, ICIC.

[18]  Yunong Zhang,et al.  Zhang neural network for online solution of time-varying convex quadratic program subject to time-varying linear-equality constraints , 2009 .

[19]  Binghuang Cai,et al.  Common Nature of Learning Exemplified by BP and Hopfield Neural Networks for Solving Online a System of Linear Equations , 2008, 2008 IEEE International Conference on Networking, Sensing and Control.

[20]  V. Hernandez,et al.  Solving linear matrix equations in control problems on distributed memory multiprocessors , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[21]  Abdullah Kurt,et al.  Modelling of the cutting tool stresses in machining of Inconel 718 using artificial neural networks , 2009, Expert Syst. Appl..

[22]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[23]  P. Hartman.  Ordinary Differential Equations , 1965 .

[24]  Charles R. Johnson,et al.  Topics in Matrix Analysis , 1991 .

[25]  Yunong Zhang,et al.  Global exponential convergence and stability of Wang neural network for solving online linear equations , 2008 .

[26]  Yunong Zhang,et al.  A set of nonlinear equations and inequalities arising in robotics and its online solution via a primal neural network , 2006, Neurocomputing.

[27]  Michael M. Li,et al.  Mutual complement between statistical and neural network approaches for rock magnetism data analysis , 2009, Expert Syst. Appl..

[28]  Christopher P. Arnold,et al.  An Efficient Parallel Algorithm for the Solution of Large Sparse Linear Matrix Equations , 1983, IEEE Transactions on Computers.

[29]  Shuzhi Sam Ge,et al.  Adaptive Neural Network Control of Robotic Manipulators , 1999, World Scientific Series in Robotics and Intelligent Systems.

[30]  Yunong Zhang,et al.  Comparison on Zhang neural network and gradient neural network for time-varying linear matrix equation AXB = C solving , 2008, 2008 IEEE International Conference on Industrial Technology.