Title :
Neural networks as an aid to iterative optimization methods
Author :
Li, H.J. ; Sung, A.H. ; Weiss, W.W. ; Wo, S.C.
Author_Institution :
Dept. of Comput. Sci., New Mexico Tech., Socorro, NM, USA
Abstract :
This paper presents an approach of using neural networks to select starting points for iterative methods for optimization problems. Since input/output training data are often available or easily obtained from the problem description, a neural network can be trained to provide a rough model of the optimization problem. After the neural network is trained, it is used to select starting points for the iterative algorithm. We illustrate the potential of this approach with examples
Keywords :
iterative methods; neural nets; optimisation; I/O training data; input/output training data; iterative optimization methods; neural networks; starting point selection; Artificial neural networks; Computer science; Data engineering; Iterative algorithms; Iterative methods; Neural networks; Nonlinear systems; Optimization methods; Predictive models; Training data;
Conference_Titel :
Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4778-1
DOI :
10.1109/ICSMC.1998.728158
