A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints

Qingshan Liu; Jun Wang

doi:10.1007/11893257_110

A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints

Qingshan Liu
, Jun Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

19 Citations (Scopus)

Abstract

In this paper, a recurrent neural network model is proposed for solving non-smooth convex programming problems, which is a natural extension of the previous neural networks. By using the non-smooth analysis and the theory of differential inclusions, the global convergence of the equilibrium is analyzed and proved. One simulation example shows the convergence of the presented neural network. © Springer-Verlag Berlin Heidelberg 2006.

Original language	English
Title of host publication	Neural Information Processing
Subtitle of host publication	13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part II
Editors	Irwin King, Jun Wang, Lai-Wan Chan
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	1004-1013
ISBN (Electronic)	978-3-540-46482-2
ISBN (Print)	9783540464815
DOIs	https://doi.org/10.1007/11893257_110
Publication status	Published - 2006
Externally published	Yes
Event	13th International Conference on Neural Information Processing (ICONIP 2006) - Hong Kong, China Duration: 3 Oct 2006 → 6 Oct 2006

Publication series

Name	Lecture Notes in Computer Science
Volume	4233
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	13th International Conference on Neural Information Processing (ICONIP 2006)
Place	China
City	Hong Kong
Period	3/10/06 → 6/10/06

Access Output

10.1007/11893257_110

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Liu, Q., & Wang, J. (2006). A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints. In I. King, J. Wang, & L.-W. Chan (Eds.), Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part II (pp. 1004-1013). (Lecture Notes in Computer Science ; Vol. 4233). Springer . https://doi.org/10.1007/11893257_110

Liu, Qingshan ; Wang, Jun. / A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints. Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part II. editor / Irwin King ; Jun Wang ; Lai-Wan Chan. Berlin, Heidelberg : Springer , 2006. pp. 1004-1013 (Lecture Notes in Computer Science ).

@inproceedings{e0c2cea5b01b4bba87a36363b04fd809,

title = "A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints",

abstract = "In this paper, a recurrent neural network model is proposed for solving non-smooth convex programming problems, which is a natural extension of the previous neural networks. By using the non-smooth analysis and the theory of differential inclusions, the global convergence of the equilibrium is analyzed and proved. One simulation example shows the convergence of the presented neural network. {\textcopyright} Springer-Verlag Berlin Heidelberg 2006.",

author = "Qingshan Liu and Jun Wang",

year = "2006",

doi = "10.1007/11893257\_110",

language = "English",

isbn = "9783540464815",

series = "Lecture Notes in Computer Science ",

publisher = "Springer ",

pages = "1004--1013",

editor = "King, \{Irwin \} and Wang, \{Jun \} and Chan, \{Lai-Wan \}",

booktitle = "Neural Information Processing",

note = "13th International Conference on Neural Information Processing (ICONIP 2006) ; Conference date: 03-10-2006 Through 06-10-2006",

}

Liu, Q & Wang, J 2006, A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints. in I King, J Wang & L-W Chan (eds), Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part II. Lecture Notes in Computer Science , vol. 4233, Springer , Berlin, Heidelberg, pp. 1004-1013, 13th International Conference on Neural Information Processing (ICONIP 2006), Hong Kong, China, 3/10/06. https://doi.org/10.1007/11893257_110

A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints. / Liu, Qingshan; Wang, Jun.
Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part II. ed. / Irwin King; Jun Wang; Lai-Wan Chan. Berlin, Heidelberg: Springer , 2006. p. 1004-1013 (Lecture Notes in Computer Science ; Vol. 4233).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints

AU - Liu, Qingshan

AU - Wang, Jun

PY - 2006

Y1 - 2006

N2 - In this paper, a recurrent neural network model is proposed for solving non-smooth convex programming problems, which is a natural extension of the previous neural networks. By using the non-smooth analysis and the theory of differential inclusions, the global convergence of the equilibrium is analyzed and proved. One simulation example shows the convergence of the presented neural network. © Springer-Verlag Berlin Heidelberg 2006.

AB - In this paper, a recurrent neural network model is proposed for solving non-smooth convex programming problems, which is a natural extension of the previous neural networks. By using the non-smooth analysis and the theory of differential inclusions, the global convergence of the equilibrium is analyzed and proved. One simulation example shows the convergence of the presented neural network. © Springer-Verlag Berlin Heidelberg 2006.

UR - https://www.scopus.com/pages/publications/33750705261

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-33750705261&origin=recordpage

U2 - 10.1007/11893257_110

DO - 10.1007/11893257_110

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9783540464815

T3 - Lecture Notes in Computer Science

SP - 1004

EP - 1013

BT - Neural Information Processing

A2 - King, Irwin

A2 - Wang, Jun

A2 - Chan, Lai-Wan

PB - Springer

CY - Berlin, Heidelberg

T2 - 13th International Conference on Neural Information Processing (ICONIP 2006)

Y2 - 3 October 2006 through 6 October 2006

ER -

Liu Q, Wang J. A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints. In King I, Wang J, Chan LW, editors, Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part II. Berlin, Heidelberg: Springer . 2006. p. 1004-1013. (Lecture Notes in Computer Science ). Epub 2006 Oct 3. doi: 10.1007/11893257_110

A recurrent neural network for non-smooth convex programming subject to linear equality and bound constraints

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this