| Article ID: | iaor1997121 |
| Country: | Netherlands |
| Volume: | 69 |
| Issue: | 1 |
| Start Page Number: | 92 |
| End Page Number: | 96 |
| Publication Date: | Aug 1993 |
| Journal: | European Journal of Operational Research |
| Authors: | Kovacic Matevz |
| Keywords: | neural networks, markov processes |
A neural network which efficiently and nearly optimally solves combinatorial optimization problems was applied to the timetable problem. The network was tested on a real-world timetable problem. The results indicate that the Markovian neural network is an efficient and flexible tool for solving real-world combinatorial optimization problems such as construction of a timetable for high schools.