New error function designs for finite-time ZNN models with application to dynamic matrix inversion

Abstract The zeroing neural network (ZNN), as a special kind of recurrent neural network (RNN), is often utilized to solve dynamic matrix inversion problems in the many fields recently. In this work, two finite-time ZNN (termed as ZNN-A and ZNN-B) models with the sign-bi-power (SBP) activation function are proposed by designing two novel error functions. The theoretical analysis shows the superior stability and finite-time convergence properties of the ZNN-A and ZNN-B models. Furthermore, three simulative examples show the effectiveness of the proposed ZNN-A and ZNN-B models for finding dynamic matrix inversion and the correctness of the corresponding theorems. To reveal the superior performance of the proposed ZNN-A and ZNN-B models with SBP activation function, the standard ZNN model with the linear activation function is comparatively applied in experiments.

[1]  N. Arunkumar,et al.  Convolutional neural network for bio-medical image segmentation with hardware acceleration , 2018, Cognitive Systems Research.

[2]  Kenli Li,et al.  A robust and fixed-time zeroing neural dynamics for computing time-variant nonlinear equation using a novel nonlinear activation function , 2019, Neurocomputing.

[3]  Ramana V. Grandhi,et al.  Accelerated engineering design optimization using successive matrix inversion method , 2004 .

[4]  Yuehua Huang,et al.  Finite-Time Stability and Its Application for Solving Time-Varying Sylvester Equation by Recurrent Neural Network , 2014, Neural Processing Letters.

[5]  U. Rajendra Acharya,et al.  Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals , 2017, Comput. Biol. Medicine.

[6]  Chao Gao,et al.  An Iterative Thresholding Segmentation Model Using a Modified Pulse Coupled Neural Network , 2013, Neural Processing Letters.

[7]  Lin Xiao.  A finite-time convergent Zhang neural network and its application to real-time matrix square root finding , 2017, Neural Computing and Applications.

[8]  Shuai Li,et al.  Discrete-time noise-tolerant Zhang neural network for dynamic matrix pseudoinversion , 2019, Soft Comput..

[9]  M. N. Nahas.  Using Modeling in Intellectual Capital , 2016 .

[10]  Shuai Li,et al.  RNN Models for Dynamic Matrix Inversion: A Control-Theoretical Perspective , 2018, IEEE Transactions on Industrial Informatics.

[11]  Yunong Zhang,et al.  Different Complex ZFs Leading to Different Complex ZNN Models for Time-Varying Complex Generalized Inverse Matrices , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Nidhi Sharma.  Space Time Block Code for Next Generation Multi-user MIMO Systems , 2014, FNC/MobiSPC.

[13]  Victor Y. Pan,et al.  An Improved Newton Iteration for the Generalized Inverse of a Matrix, with Applications , 1991, SIAM J. Sci. Comput..

[14]  Yunong Zhang,et al.  Zhang Neural Network Versus Gradient Neural Network for Solving Time-Varying Linear Inequalities , 2011, IEEE Transactions on Neural Networks.

[15]  Ning Wang,et al.  Adaptive Robust Finite-Time Trajectory Tracking Control of Fully Actuated Marine Surface Vehicles , 2016, IEEE Transactions on Control Systems Technology.

[16]  Jian Liu,et al.  Fixed-Time Leader–Follower Consensus of Networked Nonlinear Systems via Event/Self-Triggered Control , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Yongsheng Zhang,et al.  A new noise-tolerant and predefined-time ZNN model for time-dependent matrix inversion , 2019, Neural Networks.

[18]  Zeshan Hu,et al.  Design and analysis of new complex zeroing neural network for a set of dynamic complex linear equations , 2019, Neurocomputing.

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

[20]  J. M. Sellier,et al.  A new Walk on Equations Monte Carlo method for solving systems of linear algebraic equations , 2015 .

[21]  Lin Xiao,et al.  Design and Comprehensive Analysis of a Noise-Tolerant ZNN Model With Limited-Time Convergence for Time-Dependent Nonlinear Minimization , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Lin Xiao,et al.  New Varying-Parameter ZNN Models With Finite-Time Convergence and Noise Suppression for Time-Varying Matrix Moore–Penrose Inversion , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[23]  Lin Xiao,et al.  A New RNN Model With a Modified Nonlinear Activation Function Applied to Complex-Valued Linear Equations , 2018, IEEE Access.

[24]  Shuzhi Sam Ge,et al.  Adaptive Predictive Control Using Neural Network for a Class of Pure-Feedback Systems in Discrete Time , 2008, IEEE Transactions on Neural Networks.

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

[26]  Yongsheng Zhang,et al.  Performance Benefits of Robust Nonlinear Zeroing Neural Network for Finding Accurate Solution of Lyapunov Equation in Presence of Various Noises , 2019, IEEE Transactions on Industrial Informatics.

[27]  Inkyu Lee,et al.  Generalized channel inversion methods for multiuser MIMO systems , 2009, IEEE Transactions on Communications.

[28]  Yao Yu,et al.  Fixed-Time Event-Triggered Consensus for Nonlinear Multiagent Systems Without Continuous Communications , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[29]  Jian Yang,et al.  A new recurrent neural network with noise-tolerance and finite-time convergence for dynamic quadratic minimization , 2018, Neurocomputing.

[30]  Nilanjan Dey,et al.  Particle swarm optimization trained neural network for structural failure prediction of multistoried RC buildings , 2016, Neural Computing and Applications.

[31]  Wei He,et al.  Adaptive Fuzzy Neural Network Control for a Constrained Robot Using Impedance Learning , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[32]  Predrag S. Stanimirović,et al.  Improved GNN Models for Constant Matrix Inversion , 2019, Neural Processing Letters.

[33]  Yunong Zhang,et al.  Two New Types of Zhang Neural Networks Solving Systems of Time-Varying Nonlinear Inequalities , 2012, IEEE Transactions on Circuits and Systems I: Regular Papers.

[34]  Kenli Li,et al.  A novel recurrent neural network and its finite-time solution to time-varying complex matrix inversion , 2019, Neurocomputing.

[35]  Meng Joo Er,et al.  Generalized Single-Hidden Layer Feedforward Networks for Regression Problems , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[36]  Meng Joo Er,et al.  Parsimonious Extreme Learning Machine Using Recursive Orthogonal Least Squares , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[37]  Yanjun Shen,et al.  Discrete-time neural network with two classes of bias noises for solving time-variant matrix inversion and application to robot tracking , 2019, Neural Computing and Applications.

[38]  Shuai Li,et al.  Solving Time-Varying System of Nonlinear Equations by Finite-Time Recurrent Neural Networks With Application to Motion Tracking of Robot Manipulators , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[39]  Ke Chen.  Recurrent implicit dynamics for online matrix inversion , 2013, Appl. Math. Comput..

[40]  Chuan Tang,et al.  High Precision Low Complexity Matrix Inversion Based on Newton Iteration for Data Detection in the Massive MIMO , 2016, IEEE Communications Letters.

[41]  Shuai Li,et al.  Accelerating a Recurrent Neural Network to Finite-Time Convergence for Solving Time-Varying Sylvester Equation by Using a Sign-Bi-power Activation Function , 2012, Neural Processing Letters.

[42]  Shuai Li,et al.  Zeroing neural-dynamics approach and its robust and rapid solution for parallel robot manipulators against superposition of multiple disturbances , 2018, Neurocomputing.

[43]  Shuai Li,et al.  Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations , 2018, Neural Networks.

[44]  Ning Wang,et al.  Global asymptotic output tracking of nonlinear second-order systems with power integrators , 2017, Autom..

[45]  Kodjo Agbossou,et al.  Time series prediction using artificial wavelet neural network and multi-resolution analysis: Application to wind speed data , 2016 .