A Neural Network for Moore-Penrose Inverse of Time-Varying Complex-Valued Matrices

被引：18

作者：

Chai, Yiyuan ^{[1
]}

Li, Haojin ^{[2
]}

Qiao, Defeng ^{[2
]}

Qin, Sitian ^{[2
]}

Feng, Jiqiang ^{[1
]}

机构：

[1] Shenzhen Univ, Coll Math & Stat, Shenzhen Key Lab Adv Machine Learning & Applicat, Shenzhen 518060, Peoples R China

[2] Harbin Inst Technol, Dept Math, Weihai 264209, Peoples R China

来源：

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS | 2020年 / 13卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Zhang neural network; MoorePenrose inverse; Finite-time convergence; Noise suppression; SYLVESTER EQUATION; CONVERGENCE; MODEL;

D O I：

10.2991/ijcis.d.200527.001

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The MoorePenrose inverse of a matrix plays a very important role in practical applications. In general, it is not easy to immediately solve the MoorePenrose inverse of a matrix, especially for solving the MoorePenrose inverse of a complex-valued matrix in time-varying situations. To solve this problem conveniently, in this paper, a novel Zhang neural network (ZNN) with time-varying parameter that accelerates convergence is proposed, which can solve MoorePenrose inverse of a matrix over complex field in real time. Analysis results show that the state solutions of the proposed model can achieve super convergence in finite time with weighted sign-bi-power activation function (WSBP) and the upper bound of the convergence time is calculated. A related noise-tolerance model which possesses finite-time convergence property is proved to be more efficient in noise suppression. At last, numerical simulation illustrates the performance of the proposed model as well. (C) 2020 The Authors. Published by Atlantis Press SARL.

引用

页码：663 / 671

页数：9

共 36 条

[1] Fitzpatrick functions and continuous linear monotone operators [J].

Bauschke, Heinz H. ;

Borwein, Jonathan M. ;

Wang, Xianfu .

SIAM JOURNAL ON OPTIMIZATION, 2007, 18 (03) :789-809

[2]

CHEN LJ, 1994, PARALLEL COMPUT, V20, P297, DOI 10.1016/S0167-8191(06)80014-1

[3] Monostability and Bistability of Boolean Networks Using Semitensor Products [J].

Chen, Shuqi ;

Wu, Yuhu ;

Macauley, Matthew ;

Sun, Xi-Ming .

IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2019, 6 (04) :1379-1390

[4]

Ding ST, 2016, PROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), P210, DOI 10.1109/WCICA.2016.7578305

[5] The Moore-Penrose generalized inverse for sums of matrices [J].

Fill, JA ;

Fishkind, DE .

SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2000, 21 (02) :629-635

[6] Li-function activated ZNN with finite-time convergence applied to redundant-manipulator kinematic control via time-varying Jacobian matrix pseudoinversion [J].

Guo, Dongsheng ;

Zhang, Yunong .

APPLIED SOFT COMPUTING, 2014, 24 :158-168

[7] Zhang neural network versus gradient-based neural network for time-varying linear matrix equation solving [J].

Guo, Dongsheng ;

Yi, Chenfu ;

Zhang, Yunong .

NEUROCOMPUTING, 2011, 74 (17) :3708-3712

[8] Nonconvex function activated zeroing neural network models for dynamic quadratic programming subject to equality and inequality constraints [J].

Jin, Long ;

Li, Shuai .

NEUROCOMPUTING, 2017, 267 :107-113

[9] Chaotic Time Series Prediction Based on a Novel Robust Echo State Network [J].

Li, Decai ;

Han, Min ;

Wang, Jun .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (05) :787-799

[10] Accelerating a Recurrent Neural Network to Finite-Time Convergence for Solving Time-Varying Sylvester Equation by Using a Sign-Bi-power Activation Function [J].

Li, Shuai ;

Chen, Sanfeng ;

Liu, Bo .

NEURAL PROCESSING LETTERS, 2013, 37 (02) :189-205

← 1 2 3 4 →