Title :
On Solving Constrained Optimization Problems with Neural Networks: A Penalty Function Method Approach
Author :
Walter E. Lillo;Stefen Hul;Mei Heng Loh;Stanislaw H. Zak
Author_Institution :
School of Electrical Engineerng, Purdue University, West Lafayette, IN 47907
fDate :
6/1/1992 12:00:00 AM
Abstract :
This paper is concerned with utilizng analog circuits to solve various linear and nonlinear programming problems. The dynamics of these circuits are analyzed. A new nonlinear programming network and its circuit implementation is introduced which utilizes the nonlinearities to eliminate the problems encountered in previous circuit implementations.
Keywords :
"Constraint optimization","Neural networks","Dynamic programming","Circuit simulation","Intelligent networks","Analog circuits","Linear programming","Mathematical programming","Circuit analysis","Hopfield neural networks"
Conference_Titel :
American Control Conference, 1992
Print_ISBN :
0-7803-0210-9
