Application of an annealed neural network to a timetabling problem

Application of an annealed neural network to a timetabling problem

0.00 Avg rating0 Votes
Article ID: iaor19971878
Country: United States
Volume: 8
Issue: 2
Start Page Number: 103
End Page Number: 117
Publication Date: Apr 1996
Journal: INFORMS Journal On Computing
Authors: , ,
Keywords: neural networks
Abstract:

In this paper, the authors use an annealed neural network to solve a timetabling problem with contiguity and availability constraints. A novel feature of the problem is that it may not be possible to satisfy the complete set of scheduling requirements, forcing the network to exhibit selection capability. They formulate the problem in a manner consistent with neural computation, describe our implementation of the annealed neural network, and report computational results for a series of randomly-generated problems. Solution quality varies depending on the size and difficulty of the problem, as well as on the values of the penalty parameters used to weight the various constraints.

Reviews

Required fields are marked *. Your email address will not be published.