Title :
On solving constrained optimization problems with neural networks
Author :
Glazos, M.P. ; Hui, Stefen ; Zak, Stanislaw H.
Author_Institution :
Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
We analyze a class of neural networks that solve convex programming problems. In carrying out the analysis we use concepts from the theory of differential equations with discontinuous right-hand sides and Lyapunov stability theory. We show that irrespective of the initial state of the network the state converges to a solution of the convex programming problem. The dynamic behavior of the networks is illustrated by two numerical examples
Keywords :
Lyapunov methods; convex programming; differential equations; neural nets; nonlinear programming; optimisation; Lyapunov stability theory; constrained optimization; convex programming; differential equations; neural networks; state converges; Constraint optimization; Design optimization; Differential equations; Intelligent networks; Lyapunov method; Mathematical programming; Neural networks; Switched capacitor networks;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.375006
