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
fDate :
5/1/1996 12:00:00 AM
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;
Journal_Title :
Neural Networks, IEEE Transactions on
