Article ID: | iaor2004998 |
Country: | United States |
Volume: | 20 |
Issue: | 4 |
Start Page Number: | 208 |
End Page Number: | 231 |
Publication Date: | Oct 2003 |
Journal: | Expert Systems |
Authors: | Rolland E., Wang H., Jacob V. |
Keywords: | neural networks, artificial intelligence: expert systems |
Although neural networks have been successfully used in performing pattern recognition, their application for solving optimization problems has been limited. In this paper we design a neural network to solve a well-known combinatorial problem, namely the flexible flow shop problem. A key feature of our neural network design is the integration of problem structure and heuristic information in the network structure and solution. We compare the performance of our neural network with well-known current heuristics with respect to solution quality. The results indicate that our approach outperfoms the heuristics.