Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

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
Country of Publication:
United States
Language:
English

Similar Records

A robust and efficient training algorithm for feedforward neural networks
Thesis/Dissertation · Mon Dec 31 23:00:00 EST 1990 · OSTI ID:7033768

Nonlinear PLS modeling using neural networks
Conference · Fri Dec 30 23:00:00 EST 1994 · OSTI ID:81589

Multilayer perceptron for nonlinear programming.
Journal Article · Thu Aug 01 00:00:00 EDT 2002 · Comput. Oper. Res. · OSTI ID:943019