Nonlinear programming with feedforward neural networks.
Conference
·
OSTI ID:11194
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 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.
- Research Organization:
- Argonne National Lab., IL (US)
- Sponsoring Organization:
- US Department of Energy (US)
- DOE Contract Number:
- W-31109-ENG-38
- OSTI ID:
- 11194
- Report Number(s):
- ANL/RA/CP-98069; TRN: AH200128%%653
- Resource Relation:
- Conference: International Joint Conference on Neural Networks '99, Washington, DC (US), 07/10/1999--07/16/1999; Other Information: PBD: 2 Jun 1999
- Country of Publication:
- United States
- Language:
- English
Similar Records
Nonlinear PLS modeling using neural networks
Nonlinear identification of process dynamics using neural networks
A robust and efficient training algorithm for feedforward neural networks
Conference
·
Sat Dec 31 00:00:00 EST 1994
·
OSTI ID:11194
Nonlinear identification of process dynamics using neural networks
Journal Article
·
Wed Jan 01 00:00:00 EST 1992
· Nuclear Technology; (United States)
·
OSTI ID:11194
+1 more
A robust and efficient training algorithm for feedforward neural networks
Miscellaneous
·
Tue Jan 01 00:00:00 EST 1991
·
OSTI ID:11194