Different Zhang functions leading to different ZNN models illustrated via time-varying matrix square roots finding

In view of the great potential in parallel processing and ready implementation via hardware, neural networks are now often employed to solve online nonlinear matrix equation problems. Recently, a novel class of neural networks, termed Zhang neural network (ZNN), has been formally proposed by Zhang et al. for solving online time-varying problems. Such a neural-dynamic system is elegantly designed by defining an indefinite matrix-valued error-monitoring function, which is called Zhang function (ZF). The dynamical system is then cast in the form of a first-order differential equation by using matrix notation. In this paper, different indefinite ZFs, which lead to different ZNN models, are proposed and developed as the error-monitoring functions for time-varying matrix square roots finding. Towards the final purpose of field programmable gate array (FPGA) and application-specific integrated circuit (ASIC) realization, the MATLAB Simulink modeling and verifications of such ZNN models are further investigated for online solution of time-varying matrix square roots. Both theoretical analysis and modeling results substantiate the efficacy of the proposed ZNN models for time-varying matrix square roots finding.

[1]  Seyyed Ali Seyyedsalehi,et al.  Towards designing modular recurrent neural networks in learning protein secondary structures , 2012, Expert Syst. Appl..

[2]  Charles R. Johnson,et al.  Uniqueness of matrix square roots and an application , 2001 .

[3]  Jun Wang,et al.  Recurrent Neural Networks for Computing Pseudoinverses of Rank-Deficient Matrices , 1997, SIAM J. Sci. Comput..

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

[5]  Lei Zhang,et al.  Newton's method with exact line search for the square root of a matrix , 2008 .

[6]  Ke Chen,et al.  MATLAB Simulation of Zhang Neural Networks for Time-Varying Sylvester Equation Solving , 2008 .

[7]  Abir Jaafar Hussain,et al.  Dynamic Ridge Polynomial Neural Network: Forecasting the univariate non-stationary and stationary trading signals , 2011, Expert Syst. Appl..

[8]  Yunong Zhang,et al.  Improved Zhang neural network model and its solution of time-varying generalized linear matrix equations , 2010, Expert Syst. Appl..

[9]  Chia-Feng Juang,et al.  Dynamic programming prediction errors of recurrent neural fuzzy networks for speech recognition , 2009, Expert Syst. Appl..

[10]  Horst R. Thieme,et al.  Global stability of the endemic equilibrium in infinite dimension: Lyapunov functions and positive operators , 2011 .

[11]  Yunong Zhang.  On the LVI-based primal-dual neural network for solving online linear and quadratic programming problems , 2005, Proceedings of the 2005, American Control Conference, 2005..

[12]  Dongsheng Guo,et al.  Zhang neural network and its application to Newton iteration for matrix square root estimation , 2010, Neural Computing and Applications.

[13]  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.

[14]  P. E. Uys,et al.  Efficient optimisation of a vehicle suspension system, using a gradient-based approximation method, Part 1: Mathematical modelling , 2009, Math. Comput. Model..

[15]  Jun Wang,et al.  A recurrent neural network for solving Sylvester equation with time-varying coefficients , 2002, IEEE Trans. Neural Networks.

[16]  Peng-Fei Yao,et al.  On the Nonnegative Square Root of the Fourth Derivative Operators , 1998 .

[17]  Ke Chen,et al.  Performance Analysis of Gradient Neural Network Exploited for Online Time-Varying Matrix Inversion , 2009, IEEE Transactions on Automatic Control.

[18]  Yunong Zhang,et al.  Time-series Gaussian Process Regression Based on Toeplitz Computation of O(N2) Operations and O(N)-level Storage , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[19]  Ke Chen,et al.  Global exponential convergence and stability of gradient-based neural network for online matrix inversion , 2009, Appl. Math. Comput..

[20]  Binghuang Cai,et al.  From Zhang Neural Network to Newton Iteration for Matrix Inversion , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[21]  M.A. Shanblatt,et al.  A Simulink-to-FPGA implementation tool for enhanced design flow [educational applications] , 2005, 2005 IEEE International Conference on Microelectronic Systems Education (MSE'05).

[22]  Yunong Zhang,et al.  Different Zhang functions leading to different Zhang-dynamics models illustrated via time-varying reciprocal solving , 2012 .

[23]  Mohammed A. Hasan,et al.  Fixed point iterations for computing square roots and the matrix sign function of complex matrices , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[24]  Wen Yu,et al.  Stability Analysis of Nonlinear System Identification via Delayed Neural Networks , 2007, IEEE Transactions on Circuits and Systems II: Express Briefs.

[25]  Elif Derya íbeyli.  Recurrent neural networks employing Lyapunov exponents for analysis of ECG signals , 2010 .

[26]  Yunong Zhang,et al.  Simulation and Comparison of Zhang Neural Network and Gradient Neural Network Solving for Time-Varying Matrix Square Roots , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[27]  Nicholas J. Higham,et al.  Stable iterations for the matrix square root , 1997, Numerical Algorithms.