A one-layer recurrent neural network for convex programming

This paper presents a one-layer recurrent neural network for solving convex programming problems subject to linear equality and nonnegativity constraints. The number of neurons in the neural network is equal to that of decision variables in the optimization problem. Compared with the existing neural...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) Jg. 10; S. 83 - 90
Hauptverfasser: Liu, Qingshan, Wang, Jun
Format: Tagungsbericht Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2008
Schlagworte:
Artificial neural networks
Computational modeling
Computer architecture
Neurons
Optimization
Programming
Recurrent neural networks
ISBN:1424418208, 9781424418206, 9781424432196, 1424432197
ISSN:2161-4393, 1522-4899
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents a one-layer recurrent neural network for solving convex programming problems subject to linear equality and nonnegativity constraints. The number of neurons in the neural network is equal to that of decision variables in the optimization problem. Compared with the existing neural networks for optimization, the proposed neural network has lower model complexity. Moreover, the proposed neural network is proved to be globally convergent to the optimal solution(s) under some mild conditions. Simulation results show the effectiveness and performance of the proposed neural network.
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISBN:1424418208
9781424418206
9781424432196
1424432197
ISSN:2161-4393
1522-4899
DOI:10.1109/IJCNN.2008.4633771