DocumentCode
971153
Title
A high-performance neural network for solving linear and quadratic programming problems
Author
Wu, Xin-Yu ; Xia, You-shen ; Li, Jianmin ; Chen, Wai-Kai
Author_Institution
Nanjing Univ. of Posts & Telecommun., China
Volume
7
Issue
3
fYear
1996
fDate
5/1/1996 12:00:00 AM
Firstpage
643
Lastpage
651
Abstract
Two classes of high-performance neural networks for solving linear and quadratic programming problems are given. We prove that the new system converges globally to the solutions of the linear and quadratic programming problems. In a neural network, network parameters are usually not specified. The proposed models can overcome numerical difficulty caused by neural networks with network parameters and obtain desired approximate solutions of the linear and quadratic programming problems
Keywords
convergence of numerical methods; linear programming; mathematics computing; matrix algebra; neural nets; quadratic programming; approximate solutions; global convergence; high-performance neural network; linear programming; matrix algebra; quadratic programming; Analog computers; Artificial neural networks; Constraint optimization; Constraint theory; Iterative methods; Mathematical model; Neural networks; Neurons; Numerical models; Quadratic programming;
fLanguage
English
Journal_Title
Neural Networks, IEEE Transactions on
Publisher
ieee
ISSN
1045-9227
Type
jour
DOI
10.1109/72.501722
Filename
501722
Link To Document