A novel extended Li zeroing neural network for matrix inversion

被引：12

作者：

Gerontitis, Dimitrios ^{[1
]}

Mo, Changxin ^{[2
]}

Stanimirovic, Predrag S. ^{[3
]}

Tzekis, Panagiotis ^{[1
]}

Katsikis, Vasilios N. ^{[4
]}

机构：

[1] Int Hellen Univ, Dept Informat & Elect Engn, Thessaloniki, Greece

[2] Chongqing Normal Univ, Sch Math Sci, Chongqing, Peoples R China

[3] Univ Nis, Fac Sci & Math, Nish 18000, Serbia

[4] Natl & Kapodistrian Univ Athens, Dept Econ, Athens 10559, Greece

来源：

NEURAL COMPUTING & APPLICATIONS | 2023年 / 35卷 / 19期

基金：

中国国家自然科学基金;

关键词：

Li zeroing neural network; Finite convergence; Matrix inverse; Extended sign-bi-power; Activation function; SLIDING MODE CONTROL; FINITE-TIME; ACTIVATION FUNCTIONS; ROBUSTNESS ANALYSIS; ZNN MODELS; CONVERGENCE; DESIGN; DYNAMICS; EQUATION; SIMULATION;

D O I：

10.1007/s00521-023-08460-w

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An improved activation function, termed extended sign-bi-power (Esbp), is proposed. An extension of the Li zeroing neural network (ELi-ZNN) based on the Esbp activation is derived to obtain the online solution of the time-varying inversion problem. A detailed theoretical analysis confirms that the new activation function accomplishes fast convergence in calculating the time-varying matrix inversion. At the same time, illustrative numerical experiments substantiate the excellent performance of the proposed activation function over the Li and tunable activation functions. Convergence properties and numerical behaviors of the proposed ELi-ZNN model are examined.

引用

页码：14129 / 14152

页数：24

共 90 条

[1]

[Anonymous], 2011, Zhang Neural Networks and Neural-dynamic Method

[2]

Boyat A.K., 2015, ARXIV

[3] Application of ADI iterative methods to the restoration of noisy images [J].

Calvetti, D ;

Reichel, L .

SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 1996, 17 (01) :165-186

[4] Robustness analysis of Wang neural network for online linear equation solving [J].

Chen, K. .

ELECTRONICS LETTERS, 2012, 48 (22) :1391-1392

[5] Robustness analysis of a hybrid of recursive neural dynamics for online matrix inversion [J].

Chen, Ke ;

Yi, Chenfu .

APPLIED MATHEMATICS AND COMPUTATION, 2016, 273 :969-975

[6] Recurrent implicit dynamics for online matrix inversion [J].

Chen, Ke .

APPLIED MATHEMATICS AND COMPUTATION, 2013, 219 (20) :10218-10224

[7]

Cichocki A., 1992, B POLISH ACAD SCI TE, V40, P387

[8] ZNN With Fuzzy Adaptive Activation Functions and Its Application to Time-Varying Linear Matrix Equation [J].

Dai, Jianhua ;

Yang, Xing ;

Xiao, Lin ;

Jia, Lei ;

Li, Yiwei .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (04) :2560-2570

[9] Design and Analysis of Two Prescribed-Time and Robust ZNN Models With Application to Time-Variant Stein Matrix Equation [J].

Dai, Jianhua ;

Jia, Lei ;

Xiao, Lin .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (04) :1668-1677

[10] Two Novel Finite Time Convergent Recurrent Neural Networks for Tackling Complex-Valued Systems of Linear Equation [J].

Ding, Lei ;

Xiao, Lin ;

Zhou, Kaiqing ;

Lan, Yonghong ;

Zhang, Yongsheng .

FILOMAT, 2020, 34 (15) :5009-5018

← 1 2 3 4 5 6 7 8 9 →