Abstract
A new neural network for solving job shop scheduling problems is presented. The proposed Scaling Neural Network (SNN) achieves good (linear) scaling properties by employing nonlinear processing in the feedback connections. Extensive comparisons between SNN and conventional heuristics for scheduling are presented. These comparisons indicate that the proposed SNN allows to obtain better scheduling solutions than commonly used heuristics, especially for large problems. Key words: Heuristic, job shop scheduling, neural network, scaling.
Original language | English (US) |
---|---|
Pages (from-to) | 815-825 |
Number of pages | 11 |
Journal | Proceedings of SPIE - The International Society for Optical Engineering |
Volume | 1710 |
DOIs | |
State | Published - Jul 1 1992 |
Event | Science of Artificial Neural Networks 1992 - Orlando, United States Duration: Apr 20 1992 → … |
Bibliographical note
Publisher Copyright:© 1992 Proceedings of SPIE - The International Society for Optical Engineering. All rights reserved.