×

A parallel computing method based on zeroing neural networks for time-varying complex-valued matrix Moore-Penrose inversion. (English) Zbl 07334870

Summary: This paper analyzes the existing zeroing neural network (ZNN) models from the perspective of control theory. It proposes an exclusive ZNN model for solving the dynamic complex-valued matrix Moore-Penrose inverse problem: the complex-valued zeroing neural network (CVZNN). Then, a method of constructing a special type of saturation-allowed activation function is defined, which relaxes the convex constraint on the activation function when constructing the ZNN model. The convergence of the CVZNN model activated by proposed saturation-allowed functions is analyzed. Besides, the robustness of the CVZNN model under different types of noise interference is investigated based on the perspective of the control theory. Finally, the effectiveness and superiority of the CVZNN model are illustrated by simulation experiments.

MSC:

65F20 Numerical solutions to overdetermined systems, pseudoinverses
15A09 Theory of matrix inversion and generalized inverses
65Y05 Parallel numerical computation
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Chen, J.; Li, K.; Bilal, K.; Li, K.; Yu, P. S., A bi-layered parallel training architecture for large-scale convolutional neural networks in distributed computing environments, IEEE Trans. Parallel Distrib. Syst., 30, 965-976 (2019)
[2] Chountasis, S.; Katsikis, V. N.; Pappas, D., Digital image reconstruction in the spectral domain utilizing the moore-penrose inverse, Math. Probl. Eng., 1-14 (2010) · Zbl 1189.94016
[3] Chountasis, S.; Katsikis, V. N.; Pappas, D., Applications of the moore-penrose inverse in digital image restoration, Math. Probl. Eng., 1-12 (2009) · Zbl 1191.68778
[4] Courrieu, P., Fast computation of moore-penrose inverse matrices, Neural Inf. Process. Lett. Rev., 8, 25-39 (2005)
[5] Chen, Y.; Li, K.; Yang, W.; Xiao, G.; Xie, X.; Li, T., Performance-aware model for sparse matrix-matrix multiplication on the sunwaytaihulight supercomputer, IEEE Trans. Parallel Distrib. Syst., 30, 923-938 (2019)
[6] Duan, M.; Li, K.; Liao, X.; Li, K., A parallel multiclassification algorithm for big data using an extreme learning machine, IEEE Trans. Neural Netw. Learn. Syst., 29, 2337-2351 (2018)
[7] Feldkamp, L. A.; V. Puskorius, G., A signal processing framework based on dynamic neural networks with application to problem in adaptation, filtering, and classification. Proc. IEEE., 86, 2259-2277 (1998)
[8] Guo, W.; Huang, T., Method of elementary transformation to compute moore-penrose inverse, Appl. Math. Comput., 216, 1614-1617 (2010) · Zbl 1200.65027
[9] Hirose, A.; Yoshida, S., Generalization characteristics of complexvalued feedforward neural networks in relation to signal coherence, IEEE Trans. Neural Netw. Learn. Syst., 23, 541-551 (2012)
[10] Hu, J.; Wang, J., Global stability of complex-valued recurrent neural networks with time-delays, IEEE Trans. Neural Netw. Learn. Syst., 23, 853-865 (2012)
[11] Hong, X.; Chen, S., Modeling of complex-valued wiener systems using b-spline neural network, IEEE Trans. Neural Netw., 22, 818-825 (2011)
[12] Jin, L.; Li, S.; Liao, B.; Zhang., Z., Zeroing neural networks: a survey, Neurocomputing, 267, 597-604 (2017)
[13] Jin, L.; Li, S.; Wang, H.; Zhang, Z., Nonconvex projection activated zeroing neurodynamic models for time-varying matrix pseudoinversion with accelerated finite-time convergence, Appl. Soft. Comput., 62, 840-850 (2018)
[14] Jin, L.; Zhang, Y.; Qiao, T.; Tan, M.; Zhang, Y., Tracking control of modified lorenz nonlinear system using ZG neural dynamics with additive input or mixed inputs, Neurocomputing, 196, 82-94 (2016)
[15] Liao, B.; Zhang, Y.; Jin, L., Taylor o(h^3) discretization of ZNN models for dynamic equality-constrained quadratic programming with application to manipulators, IEEE Trans. Neural Netw. Learn. Syst., 27, 225-237 (2016)
[16] Lu, H.; Jin, L.; Luo, X.; Liao, B.; Guo, D.; Xiao, L., RNN for solving perturbed time-varying underdetermined linear system with double bound limits on residual errors and state variables, IEEE Trans. Ind. Inform., 15, 5931-5942 (2019)
[17] 2015 · Zbl 1360.68276
[18] Li, K.; Yang, W.; Keqin, L., Performance analysis and optimization for spMV on GPU using probabilistic modeling, IEEE Trans. Parallel Distrib. Syst., 26, 196-205 (2015)
[19] Li, S.; Li, Y., Nonlinearly activated neural network for solving time-varying complex sylvester equation, IEEE Trans. Cyber., 44, 1397-1407 (2014)
[20] Li, S.; Zhou, M.; Luo, X.; You, Z., Distributed winner-take-all in dynamic networks, IEEE Trans. Autom. Control., 62, 577-589 (2017) · Zbl 1364.93022
[21] Lei, Y.; Liao, B.; Yin, Q., A noise-acceptable ZNN for computing complex-valued time-dependent matrix pseudoinverse, IEEE Access, 7, 13832-13841 (2019)
[22] Liu, Y.; Li, J.; Tong, S.; Chen, C. L.P., Neural network control-based adaptive learning design for nonlinear systems with full-state constraints, IEEE Trans. Neural Netw. Learning Sys., 27, 1562-1571 (2016)
[23] Liu, Y.; Tong, S., Optimal control-based adaptive NN design for a class of nonlinear discrete-time block-triangular systems, IEEE Trans. Cybern., 46, 2670-2680 (2016)
[24] Perkovic, M. D.; Stanimirovic, P. S., Iterative method for computing the moore-penrose inverse besed on penrose equations, J. Comput. Appl. Math., 235, 1604-1613 (2011) · Zbl 1206.65139
[25] Mei, J.; Li, K.; Ouyang, A.; Li, K., A profit maximization scheme with guaranteed quality of service in cloud computing, IEEE Trans. Comput, 64, 3064-3078 (2015) · Zbl 1360.68279
[26] Tan, Z.; Hu, Y.; Xiao, L.; Chen, K., Robustness analysis and robotic application of combined function activated RNN for time-varying matrix pseudo inversion, IEEE Access, 7, 33434-33440 (2019)
[27] Wang, H.; Liu, K.; Liu, X.; Chen, B.; Lin, C., Neural-based adaptive output-feedback control for a class of nonstrict-feedback stochastic nonlinear systems, IEEE Trans. Cyber., 45, 1977-1987 (2015)
[28] Wei, Y., Recurrent neural networks for computing weighted moorepenrose inverse, Appl. Math. Comput., 116, 279-287 (2000) · Zbl 1023.65030
[29] Xu, F.; Li, Z.; Nie, Z.; Shao, H.; Guo, D., Zeroing neural network for solving time-varying linear equation and inequality systems, IEEE Trans. Neural Netw. Learn. Syst., 30, 2346-2357 (2019)
[30] Xiao, G.; Li, K.; Li, K., Reporting l most influential objects in uncertain databases based on probabilistic reverse top-k queries, Inf. Sci., 405, 207-226 (2017)
[31] Xiao, L.; Jia, L.; Zhang, Y.; Hu, Z.; Dai, J., Finite-time convergence and robustness analysis of two nonlinear activated ZNN models for time-varying linear matrix equations, IEEE Access, 7, 135133-135144 (2019)
[32] Xiao, L.; Li, S.; Lin, F.; Tan, Z.; Khan, A. H., Zeroing neural dynamics for control design: comprehensive analysis on stability, robustness, and convergence speed, IEEE Trans. Ind. Informat., 15, 2605-2616 (2019)
[33] Xu, Y.; Li, K.; Hu, J.; Li, K., A genetic algorithm for task scheduling on heterogeneous computing systems using multiple priority queues, Inf. Sci., 270, 255-287 (2014) · Zbl 1341.68020
[34] Yan, J.; Xiao, X.; Li, H.; Zhang, J.; Yan, J.; Liu, M., Noise-tolerant zeroing neural network for solving non-stationary lyapunov equation, IEEE Access, 7, 41517-41524 (2019)
[35] Zhang, L.; Li, K.; Li, C.; Li, K., Bi-objective workflow scheduling of the energy consumption and reliability in heterogeneous computing systems, Inf. Sci., 379, 241-256 (2016)
[36] Zhang, L.; Li, K.; Xu, Y.; Mei, J.; Zhang, F.; Li, K., Maximizing reliability with energy conservation for parallel task scheduling in a heterogeneous cluster, Inf. Sci., 319, 113-131 (2015)
[37] Zhu, X.; Li, K.; Salah, A.; Shi, L.; Li, K., Parallel implementation of MAFFT on CUDA-enabled graphics hardware, IEEE-ACM Trans. Comput. Biol. Bioinform, 12, 205-218 (2015)
[38] Zhang, Y.; Li, S.; Kadry, S.; Liao, B., Recurrent neural network for kinematic control of redundant manipulators with periodic input disturbance and physical constraints, IEEE T. Cybern, 49, 4194-4205 (2019)
[39] Zhang, Y.; Li, Z.; Li, K., Complex-valued zhang neural network for online complex-valued time-varying matrix inversion, Appl. Math. Comput., 217, 10066-10073 (2011) · Zbl 1220.65036
[40] Zhang, Z.; Deng, X.; Qu, X.; Liao, B.; Kong, L.; Li, L., A varying-gain recurrent neural network and its application to solving online time-varying matrix equation, IEEE Access, 6, 77940-77952 (2018)
[41] Jin, L.; Yan, J.; Du, X.; Xiao, X.; Fu, D., RNN for Solving Time-Variant Generalized Sylvester Equation with Applications to Robots and Acoustic Source Localization, IEEE Trans. Ind. Inform. (2020)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.