A discrete-time switching neural network for quadratic programming

S. Chen; Shuai Li; Y. Liang; Y. Lou

doi:10.1109/IJCNN.2012.6252844

A discrete-time switching neural network for quadratic programming

S. Chen, Shuai Li, Y. Liang, Y. Lou

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

1 Citation (Scopus)

Abstract

This paper presents a discrete-time neural network with a switching structure to solve a general quadratic programming problem in real time. Compared with existing ones for solving quadratic programming problems, the proposed neural network model has a simple architecture and uses a limited number of neurons to solve the problem, irrespective of the dimension of the decision variables or the number of constraints. The global convergence of the model is proven using contraction theory. Simulations are performed to demonstrate the effectiveness of the proposed method.

Original language	English
Title of host publication	2012 International Joint Conference on Neural Networks, IJCNN 2012
DOIs	https://doi.org/10.1109/IJCNN.2012.6252844
Publication status	Published - 22 Aug 2012
Externally published	Yes
Event	2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD, Australia Duration: 10 Jun 2012 → 15 Jun 2012

Conference

Conference	2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
Country/Territory	Australia
City	Brisbane, QLD
Period	10/06/12 → 15/06/12

Keywords

contraction theory
global convergence
Neural network
quadratic programming

ASJC Scopus subject areas

Software
Artificial Intelligence

More information

10.1109/IJCNN.2012.6252844

Cite this

@inproceedings{848355764d5e48ddb6ac2f56331eeaed,

title = "A discrete-time switching neural network for quadratic programming",

abstract = "This paper presents a discrete-time neural network with a switching structure to solve a general quadratic programming problem in real time. Compared with existing ones for solving quadratic programming problems, the proposed neural network model has a simple architecture and uses a limited number of neurons to solve the problem, irrespective of the dimension of the decision variables or the number of constraints. The global convergence of the model is proven using contraction theory. Simulations are performed to demonstrate the effectiveness of the proposed method.",

keywords = "contraction theory, global convergence, Neural network, quadratic programming",

author = "S. Chen and Shuai Li and Y. Liang and Y. Lou",

year = "2012",

month = aug,

day = "22",

doi = "10.1109/IJCNN.2012.6252844",

language = "English",

isbn = "9781467314909",

booktitle = "2012 International Joint Conference on Neural Networks, IJCNN 2012",

note = "2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 ; Conference date: 10-06-2012 Through 15-06-2012",

}

Chen, S, Li, S, Liang, Y & Lou, Y 2012, A discrete-time switching neural network for quadratic programming. in 2012 International Joint Conference on Neural Networks, IJCNN 2012., 6252844, 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, Australia, 10/06/12. https://doi.org/10.1109/IJCNN.2012.6252844

TY - GEN

T1 - A discrete-time switching neural network for quadratic programming

AU - Chen, S.

AU - Li, Shuai

AU - Liang, Y.

AU - Lou, Y.

PY - 2012/8/22

Y1 - 2012/8/22

N2 - This paper presents a discrete-time neural network with a switching structure to solve a general quadratic programming problem in real time. Compared with existing ones for solving quadratic programming problems, the proposed neural network model has a simple architecture and uses a limited number of neurons to solve the problem, irrespective of the dimension of the decision variables or the number of constraints. The global convergence of the model is proven using contraction theory. Simulations are performed to demonstrate the effectiveness of the proposed method.

AB - This paper presents a discrete-time neural network with a switching structure to solve a general quadratic programming problem in real time. Compared with existing ones for solving quadratic programming problems, the proposed neural network model has a simple architecture and uses a limited number of neurons to solve the problem, irrespective of the dimension of the decision variables or the number of constraints. The global convergence of the model is proven using contraction theory. Simulations are performed to demonstrate the effectiveness of the proposed method.

KW - contraction theory

KW - global convergence

KW - Neural network

KW - quadratic programming

UR - http://www.scopus.com/inward/record.url?scp=84865104715&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2012.6252844

DO - 10.1109/IJCNN.2012.6252844

M3 - Conference article published in proceeding or book

SN - 9781467314909

BT - 2012 International Joint Conference on Neural Networks, IJCNN 2012

T2 - 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012

Y2 - 10 June 2012 through 15 June 2012

ER -

A discrete-time switching neural network for quadratic programming

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this