DocumentCode
1818666
Title
A dual neural network solving quadratic programming problems
Author
Wang, Jun ; Xia, Youshen
Author_Institution
Dept. of Mech. & Autom. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong
Volume
1
fYear
1999
fDate
1999
Firstpage
588
Abstract
We propose a dual neural network with globally exponential stability for solving quadratic programming problems with unique solutions. Compared with the Bouzerdoum-Pattison network (1993), there is no need for choosing the self-feedback or lateral connection matrices in the present network. Moreover, the size of the dual network is less than that of the original problem
Keywords
asymptotic stability; convergence of numerical methods; mathematics computing; matrix algebra; neural nets; quadratic programming; Bouzerdoum-Pattison network; convergence; dual neural network; exponential stability; lateral connection matrices; quadratic programming; self-feedback; Automation; Convergence; Design engineering; Function approximation; Hopfield neural networks; Linear matrix inequalities; Neural networks; Quadratic programming; Regression analysis; Stability;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location
Washington, DC
ISSN
1098-7576
Print_ISBN
0-7803-5529-6
Type
conf
DOI
10.1109/IJCNN.1999.831564
Filename
831564
Link To Document