Article ID: | iaor20012324 |
Country: | United States |
Volume: | 12 |
Issue: | 2 |
Start Page Number: | 150 |
End Page Number: | 162 |
Publication Date: | Mar 2000 |
Journal: | INFORMS Journal On Computing |
Authors: | Tunc Enar A., Gupta Jatinder N.D., Sexton Randall S. |
Keywords: | heuristics, neural networks |
This paper discusses the application of neural networks to select the best heuristic algorithm to solve a given scheduling problem. The two-stage hybrid flowshop with multiple identical parallel machines at the second stage is used as an example to discuss the process of selecting a scheduling heuristic through a neural-network approach. This paper uses the genetic-algorithm-based approach for training the neural network and shows that the suggested neural-network approach is quite effective and efficient for selecting the best heuristic algorithm for solving a given scheduling problem.