Dynamic Neural Network Models for Time-Varying Problem Solving: A Survey on Model Structures

Cheng Hua; Xinwei Cao; Qian Xu; Bolin Liao; Shuai Li

doi:10.1109/ACCESS.2023.3290046

Dynamic Neural Network Models for Time-Varying Problem Solving: A Survey on Model Structures

Cheng Hua
, Xinwei Cao
, Qian Xu
, Bolin Liao^*
, Shuai Li^*

^*Corresponding author for this work

Not published at VTT

Jishou University
Jiangnan University
University of Oulu
VTT (former employee or external)

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

15 Citations (Scopus)

Abstract

In recent years, neural networks have become a common practice in academia for handling complex problems. Numerous studies have indicated that complex problems can generally be formulated as a single or a set of time-varying equations. Dynamic neural networks, as powerful tools for processing time-varying problems, play an essential role in their online solution. This paper reviews recent advances in real-valued, complex-valued, and noise-tolerant dynamic neural networks for solving various time-varying problems, discusses the finite-time convergence, fixed/varying parameters, and noise tolerance properties of dynamic neural network models. This review is highly relevant for researchers and novices interested in using dynamic neural networks to solve time-varying problems.

Original language	English
Pages (from-to)	65991-66008
Number of pages	18
Journal	IEEE Access
Volume	11
DOIs	https://doi.org/10.1109/ACCESS.2023.3290046
Publication status	Published - 2023
MoE publication type	A1 Journal article-refereed

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62066015 and Grant 62006095.

Keywords

activation function
Dynamic neural networks
noise-tolerant
time-varying problems
zeroing neural network (ZNN)

Access to Document

10.1109/ACCESS.2023.3290046Licence: CC BY-NC-ND

Cite this

@article{1802d0e148294f1fad73583b4f8a913e,

title = "Dynamic Neural Network Models for Time-Varying Problem Solving: A Survey on Model Structures",

abstract = "In recent years, neural networks have become a common practice in academia for handling complex problems. Numerous studies have indicated that complex problems can generally be formulated as a single or a set of time-varying equations. Dynamic neural networks, as powerful tools for processing time-varying problems, play an essential role in their online solution. This paper reviews recent advances in real-valued, complex-valued, and noise-tolerant dynamic neural networks for solving various time-varying problems, discusses the finite-time convergence, fixed/varying parameters, and noise tolerance properties of dynamic neural network models. This review is highly relevant for researchers and novices interested in using dynamic neural networks to solve time-varying problems.",

keywords = "activation function, Dynamic neural networks, noise-tolerant, time-varying problems, zeroing neural network (ZNN)",

author = "Cheng Hua and Xinwei Cao and Qian Xu and Bolin Liao and Shuai Li",

note = "Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 62066015 and Grant 62006095. Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2023",

doi = "10.1109/ACCESS.2023.3290046",

language = "English",

volume = "11",

pages = "65991--66008",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

}

TY - JOUR

T1 - Dynamic Neural Network Models for Time-Varying Problem Solving

T2 - A Survey on Model Structures

AU - Hua, Cheng

AU - Cao, Xinwei

AU - Xu, Qian

AU - Liao, Bolin

AU - Li, Shuai

PY - 2023

Y1 - 2023

N2 - In recent years, neural networks have become a common practice in academia for handling complex problems. Numerous studies have indicated that complex problems can generally be formulated as a single or a set of time-varying equations. Dynamic neural networks, as powerful tools for processing time-varying problems, play an essential role in their online solution. This paper reviews recent advances in real-valued, complex-valued, and noise-tolerant dynamic neural networks for solving various time-varying problems, discusses the finite-time convergence, fixed/varying parameters, and noise tolerance properties of dynamic neural network models. This review is highly relevant for researchers and novices interested in using dynamic neural networks to solve time-varying problems.

AB - In recent years, neural networks have become a common practice in academia for handling complex problems. Numerous studies have indicated that complex problems can generally be formulated as a single or a set of time-varying equations. Dynamic neural networks, as powerful tools for processing time-varying problems, play an essential role in their online solution. This paper reviews recent advances in real-valued, complex-valued, and noise-tolerant dynamic neural networks for solving various time-varying problems, discusses the finite-time convergence, fixed/varying parameters, and noise tolerance properties of dynamic neural network models. This review is highly relevant for researchers and novices interested in using dynamic neural networks to solve time-varying problems.

KW - activation function

KW - Dynamic neural networks

KW - noise-tolerant

KW - time-varying problems

KW - zeroing neural network (ZNN)

UR - https://www.scopus.com/pages/publications/85163461723

U2 - 10.1109/ACCESS.2023.3290046

DO - 10.1109/ACCESS.2023.3290046

M3 - Article

AN - SCOPUS:85163461723

SN - 2169-3536

VL - 11

SP - 65991

EP - 66008

JO - IEEE Access

JF - IEEE Access

ER -

Dynamic Neural Network Models for Time-Varying Problem Solving: A Survey on Model Structures

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this