DocumentCode
1510032
Title
A new neural network for solving linear and quadratic programming problems
Author
Xia, Youshen
Author_Institution
Dept. of Math., Nanjing Univ. of Posts & Telecommun., China
Volume
7
Issue
6
fYear
1996
fDate
11/1/1996 12:00:00 AM
Firstpage
1544
Lastpage
1548
Abstract
A new neural network for solving linear and quadratic programming problems is presented and is shown to be globally convergent. The new neural network improves existing neural networks for solving these problems: it avoids the parameter turning problem, it is capable of achieving the exact solutions, and it uses only simple hardware in which no analog multipliers for variables are required. Furthermore, the network solves both the primal problems and their dual problems simultaneously
Keywords
neural nets; duality; global convergence; linear programming; neural network; parameter turning; quadratic programming; Artificial neural networks; Computer networks; Hopfield neural networks; Linear programming; Neural network hardware; Neural networks; Quadratic programming; Stability; Traveling salesman problems; Turning;
fLanguage
English
Journal_Title
Neural Networks, IEEE Transactions on
Publisher
ieee
ISSN
1045-9227
Type
jour
DOI
10.1109/72.548188
Filename
548188
Link To Document