A fully complex-valued neural network for rapid solution of complex-valued systems of linear equations

Lin Xiao; Weiwei Meng; Rongbo Lu; Xi Yang; Bolin Liao; Lei Ding

doi:10.1007/978-3-319-25393-0_49

A fully complex-valued neural network for rapid solution of complex-valued systems of linear equations

Lin Xiao, Weiwei Meng, Rongbo Lu, Xi Yang, Bolin Liao, Lei Ding

Research output: Contribution to journal › Conference article › peer-review

8 Scopus citations

Abstract

In this paper, online solution of complex-valued systems of linear equations is investigated in the complex domain. Different from the conventional real-valued neural network, which is only designed for realvalued linear equations solving, a fully complex-valued gradient neural network (GNN) is developed for online complex-valued systems of linear equations. The advantages of the proposed complex-valued GNN model decrease the unnecessary complexities in theoretical analysis, real-time computation and related applications. In addition, the theoretical analysis of the fully complex-valued GNN model is presented. Finally, simulative results substantiate the effectiveness of the fully complex-valued GNN model for online solution of the complex-valued systems of linear equations in the complex domain.

Original language	English
Pages (from-to)	444-451
Number of pages	8
Journal	Lecture Notes in Computer Science
Volume	9377 LNCS
DOIs	https://doi.org/10.1007/978-3-319-25393-0_49
State	Published - 2015
Externally published	Yes
Event	12th International Symposium on Neural Networks, ISNN 2015 - Jeju, Korea, Republic of Duration: 15 Oct 2015 → 18 Oct 2015

Keywords

Complex domain
Complex-valued linear system
Neural network
Simulation verification

Access to Document

10.1007/978-3-319-25393-0_49

Cite this

@article{7719d04fef614c069dbf6d26f2e2e62f,

title = "A fully complex-valued neural network for rapid solution of complex-valued systems of linear equations",

abstract = "In this paper, online solution of complex-valued systems of linear equations is investigated in the complex domain. Different from the conventional real-valued neural network, which is only designed for realvalued linear equations solving, a fully complex-valued gradient neural network (GNN) is developed for online complex-valued systems of linear equations. The advantages of the proposed complex-valued GNN model decrease the unnecessary complexities in theoretical analysis, real-time computation and related applications. In addition, the theoretical analysis of the fully complex-valued GNN model is presented. Finally, simulative results substantiate the effectiveness of the fully complex-valued GNN model for online solution of the complex-valued systems of linear equations in the complex domain.",

keywords = "Complex domain, Complex-valued linear system, Neural network, Simulation verification",

author = "Lin Xiao and Weiwei Meng and Rongbo Lu and Xi Yang and Bolin Liao and Lei Ding",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2015.; 12th International Symposium on Neural Networks, ISNN 2015 ; Conference date: 15-10-2015 Through 18-10-2015",

year = "2015",

doi = "10.1007/978-3-319-25393-0\_49",

language = "英语",

volume = "9377 LNCS",

pages = "444--451",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Science and Business Media Deutschland GmbH",

}

TY - JOUR

T1 - A fully complex-valued neural network for rapid solution of complex-valued systems of linear equations

AU - Xiao, Lin

AU - Meng, Weiwei

AU - Lu, Rongbo

AU - Yang, Xi

AU - Liao, Bolin

AU - Ding, Lei

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2015.

PY - 2015

Y1 - 2015

N2 - In this paper, online solution of complex-valued systems of linear equations is investigated in the complex domain. Different from the conventional real-valued neural network, which is only designed for realvalued linear equations solving, a fully complex-valued gradient neural network (GNN) is developed for online complex-valued systems of linear equations. The advantages of the proposed complex-valued GNN model decrease the unnecessary complexities in theoretical analysis, real-time computation and related applications. In addition, the theoretical analysis of the fully complex-valued GNN model is presented. Finally, simulative results substantiate the effectiveness of the fully complex-valued GNN model for online solution of the complex-valued systems of linear equations in the complex domain.

AB - In this paper, online solution of complex-valued systems of linear equations is investigated in the complex domain. Different from the conventional real-valued neural network, which is only designed for realvalued linear equations solving, a fully complex-valued gradient neural network (GNN) is developed for online complex-valued systems of linear equations. The advantages of the proposed complex-valued GNN model decrease the unnecessary complexities in theoretical analysis, real-time computation and related applications. In addition, the theoretical analysis of the fully complex-valued GNN model is presented. Finally, simulative results substantiate the effectiveness of the fully complex-valued GNN model for online solution of the complex-valued systems of linear equations in the complex domain.

KW - Complex domain

KW - Complex-valued linear system

KW - Neural network

KW - Simulation verification

UR - https://www.scopus.com/pages/publications/84984614272

U2 - 10.1007/978-3-319-25393-0_49

DO - 10.1007/978-3-319-25393-0_49

M3 - 会议文章

AN - SCOPUS:84984614272

SN - 0302-9743

VL - 9377 LNCS

SP - 444

EP - 451

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

T2 - 12th International Symposium on Neural Networks, ISNN 2015

Y2 - 15 October 2015 through 18 October 2015

ER -

A fully complex-valued neural network for rapid solution of complex-valued systems of linear equations

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this