Design and comprehensive analysis of a noise-tolerant ZNN model with limited-time convergence for time-dependent nonlinear minimization

Lin Xiao; Jianhua Dai; Rongbo Lu; Shuai Li; Jichun Li; Shoujin Wang

doi:10.1109/TNNLS.2020.2966294

Design and comprehensive analysis of a noise-tolerant ZNN model with limited-time convergence for time-dependent nonlinear minimization

Lin Xiao^*, Jianhua Dai^*, Rongbo Lu, Shuai Li, Jichun Li, Shoujin Wang

^*Corresponding author for this work

School of Computing

Research output: Contribution to journal › Article › peer-review

34 Citations (Scopus)

Abstract

Zeroing neural network (ZNN) is a powerful tool to address the mathematical and optimization problems broadly arisen in the science and engineering areas. The convergence and robustness are always co-pursued in ZNN. However, there exists no related work on the ZNN for time-dependent nonlinear minimization that achieves simultaneously limited-time convergence and inherently noise suppression. In this article, for the purpose of satisfying such two requirements, a limited-time robust neural network (LTRNN) is devised and presented to solve time-dependent nonlinear minimization under various external disturbances. Different from the previous ZNN model for this problem either with limited-time convergence or with noise suppression, the proposed LTRNN model simultaneously possesses such two characteristics. Besides, rigorous theoretical analyses are given to prove the superior performance of the LTRNN model when adopted to solve time-dependent nonlinear minimization under external disturbances. Comparative results also substantiate the effectiveness and advantages of LTRNN via solving a time-dependent nonlinear minimization problem.

Original language	English
Pages (from-to)	5339-5348
Number of pages	10
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	31
Issue number	12
DOIs	https://doi.org/10.1109/TNNLS.2020.2966294
Publication status	Published - Dec 2020

Bibliographical note

Funding Information:
Manuscript received January 2, 2019; revised September 7, 2019; accepted January 7, 2020. Date of publication February 5, 2020; date of current version December 1, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61866013, Grant 61503152, Grant 61976089, Grant 61966014, and Grant 61563017 and in part by the Natural Science Foundation of Hunan Province of China under Grant 2019JJ50478, Grant 18A289, Grant 2016JJ2101, Grant 2018TP1018, and Grant 2018RS3065. (Corresponding authors: Lin Xiao; Jianhua Dai.) Lin Xiao and Jianhua Dai are with the Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Hunan Normal University, Changsha 410081, China (e-mail: xiaolin860728@163.com; jhdai@hunnu.edu.cn).

Publisher Copyright:
© 2012 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

Limited-time convergence
nonlinear minimization
robustness
time varying
zeroing neural networks (ZNNs)
Zhang neural networks

Access to Document

10.1109/TNNLS.2020.2966294

Cite this

@article{eca08509ce914c04af673a6a6c82dd2e,

title = "Design and comprehensive analysis of a noise-tolerant ZNN model with limited-time convergence for time-dependent nonlinear minimization",

abstract = "Zeroing neural network (ZNN) is a powerful tool to address the mathematical and optimization problems broadly arisen in the science and engineering areas. The convergence and robustness are always co-pursued in ZNN. However, there exists no related work on the ZNN for time-dependent nonlinear minimization that achieves simultaneously limited-time convergence and inherently noise suppression. In this article, for the purpose of satisfying such two requirements, a limited-time robust neural network (LTRNN) is devised and presented to solve time-dependent nonlinear minimization under various external disturbances. Different from the previous ZNN model for this problem either with limited-time convergence or with noise suppression, the proposed LTRNN model simultaneously possesses such two characteristics. Besides, rigorous theoretical analyses are given to prove the superior performance of the LTRNN model when adopted to solve time-dependent nonlinear minimization under external disturbances. Comparative results also substantiate the effectiveness and advantages of LTRNN via solving a time-dependent nonlinear minimization problem. ",

keywords = "Limited-time convergence, nonlinear minimization, robustness, time varying, zeroing neural networks (ZNNs), Zhang neural networks",

author = "Lin Xiao and Jianhua Dai and Rongbo Lu and Shuai Li and Jichun Li and Shoujin Wang",

note = "Funding Information: Manuscript received January 2, 2019; revised September 7, 2019; accepted January 7, 2020. Date of publication February 5, 2020; date of current version December 1, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61866013, Grant 61503152, Grant 61976089, Grant 61966014, and Grant 61563017 and in part by the Natural Science Foundation of Hunan Province of China under Grant 2019JJ50478, Grant 18A289, Grant 2016JJ2101, Grant 2018TP1018, and Grant 2018RS3065. (Corresponding authors: Lin Xiao; Jianhua Dai.) Lin Xiao and Jianhua Dai are with the Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Hunan Normal University, Changsha 410081, China (e-mail: xiaolin860728@163.com; jhdai@hunnu.edu.cn). Publisher Copyright: {\textcopyright} 2012 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",

year = "2020",

month = dec,

doi = "10.1109/TNNLS.2020.2966294",

language = "English",

volume = "31",

pages = "5339--5348",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

number = "12",

}

TY - JOUR

T1 - Design and comprehensive analysis of a noise-tolerant ZNN model with limited-time convergence for time-dependent nonlinear minimization

AU - Xiao, Lin

AU - Dai, Jianhua

AU - Lu, Rongbo

AU - Li, Shuai

AU - Li, Jichun

AU - Wang, Shoujin

N1 - Funding Information: Manuscript received January 2, 2019; revised September 7, 2019; accepted January 7, 2020. Date of publication February 5, 2020; date of current version December 1, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61866013, Grant 61503152, Grant 61976089, Grant 61966014, and Grant 61563017 and in part by the Natural Science Foundation of Hunan Province of China under Grant 2019JJ50478, Grant 18A289, Grant 2016JJ2101, Grant 2018TP1018, and Grant 2018RS3065. (Corresponding authors: Lin Xiao; Jianhua Dai.) Lin Xiao and Jianhua Dai are with the Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Hunan Normal University, Changsha 410081, China (e-mail: xiaolin860728@163.com; jhdai@hunnu.edu.cn). Publisher Copyright: © 2012 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/12

Y1 - 2020/12

N2 - Zeroing neural network (ZNN) is a powerful tool to address the mathematical and optimization problems broadly arisen in the science and engineering areas. The convergence and robustness are always co-pursued in ZNN. However, there exists no related work on the ZNN for time-dependent nonlinear minimization that achieves simultaneously limited-time convergence and inherently noise suppression. In this article, for the purpose of satisfying such two requirements, a limited-time robust neural network (LTRNN) is devised and presented to solve time-dependent nonlinear minimization under various external disturbances. Different from the previous ZNN model for this problem either with limited-time convergence or with noise suppression, the proposed LTRNN model simultaneously possesses such two characteristics. Besides, rigorous theoretical analyses are given to prove the superior performance of the LTRNN model when adopted to solve time-dependent nonlinear minimization under external disturbances. Comparative results also substantiate the effectiveness and advantages of LTRNN via solving a time-dependent nonlinear minimization problem.

AB - Zeroing neural network (ZNN) is a powerful tool to address the mathematical and optimization problems broadly arisen in the science and engineering areas. The convergence and robustness are always co-pursued in ZNN. However, there exists no related work on the ZNN for time-dependent nonlinear minimization that achieves simultaneously limited-time convergence and inherently noise suppression. In this article, for the purpose of satisfying such two requirements, a limited-time robust neural network (LTRNN) is devised and presented to solve time-dependent nonlinear minimization under various external disturbances. Different from the previous ZNN model for this problem either with limited-time convergence or with noise suppression, the proposed LTRNN model simultaneously possesses such two characteristics. Besides, rigorous theoretical analyses are given to prove the superior performance of the LTRNN model when adopted to solve time-dependent nonlinear minimization under external disturbances. Comparative results also substantiate the effectiveness and advantages of LTRNN via solving a time-dependent nonlinear minimization problem.

KW - Limited-time convergence

KW - nonlinear minimization

KW - robustness

KW - time varying

KW - zeroing neural networks (ZNNs)

KW - Zhang neural networks

UR - http://www.scopus.com/inward/record.url?scp=85083839275&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2020.2966294

DO - 10.1109/TNNLS.2020.2966294

M3 - Article

C2 - 32031952

AN - SCOPUS:85083839275

SN - 2162-237X

VL - 31

SP - 5339

EP - 5348

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 12

ER -

Design and comprehensive analysis of a noise-tolerant ZNN model with limited-time convergence for time-dependent nonlinear minimization

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this