DocumentCode
582095
Title
A high performance neural network for solving quadratic programming with hybrid constraints
Author
Xu, Xianyun ; Yang, Yongqing ; Gao, Yun
Author_Institution
Sch. of Sci., Jiangnan Univ., Wuxi, China
fYear
2012
fDate
25-27 July 2012
Firstpage
3261
Lastpage
3266
Abstract
A high performance neural network is proposed in this paper for solving quadratic programming problems with hybrid constraints. Comparing with the existing neural networks for solving such problems, the proposed neural network has fewer neurons and an one-layer architecture. The proposed neural network is proven to be global convergence. Furthermore, illustrative examples are given to show the effectiveness of the proposed neural network.
Keywords
convergence of numerical methods; mathematics computing; neural net architecture; quadratic programming; global convergence; high-performance neural network; hybrid constraints; neurons; one-layer architecture; quadratic programming; Biological neural networks; Convergence; Educational institutions; Equations; Quadratic programming; Trajectory; Convergence; Neural network; Positive semidefinite; Quadratic programming; Stability;
fLanguage
English
Publisher
ieee
Conference_Titel
Control Conference (CCC), 2012 31st Chinese
Conference_Location
Hefei
ISSN
1934-1768
Print_ISBN
978-1-4673-2581-3
Type
conf
Filename
6390484
Link To Document