Title :
Nonlinear programming with feedforward neural networks
Author :
Reifman, Jaques ; Feldman, Earl E.
Author_Institution :
Reactor Anal. Div., Argonne Nat. Lab., IL, USA
Abstract :
We provide a practical and effective method for solving constrained optimization problems by successively training a multilayer feedforward neural network in a coupled neural-network/objective-function representation. Nonlinear programming problems are easily mapped into this representation which has a simpler and more transparent method of solution than the optimization performed with Hopfield-like networks and poses very mild requirements on the functions appearing in the problem. Simulation results are illustrated and compared with an off-the-shelf-optimization tool
Keywords :
feedforward neural nets; learning (artificial intelligence); mathematics computing; nonlinear programming; constrained optimization; feedforward neural network; learning; nonlinear programming; objective-function; Constraint optimization; Feedforward neural networks; Functional programming; Inductors; Laboratories; Linear programming; Multi-layer neural network; Neural networks; Optimization methods; Vectors;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.831565
