HighPerformance Computing and Networking
Volume 1593 of the series Lecture Notes in Computer Science pp 450459
Recurrent neural network approach for partitioning irregular graphs
 MTahar KechadiAffiliated withParallel Computational Research Group, Department of Computer Science, University College Dublin
Abstract
This paper is concerned with utilizing a neural network approach to solve the kway partitioning problem. The kway partitioning is modeled as a constraint satisfaction problem with linear inequalities and binary variables. A new recurrent neural network architecture is proposed for kway partitioning. This network is based on an energy function that controls the competition between the partition's external cost and the penalty function. This method is implemented and compared to other global search techniques such as simulated annealing and genetic algorithms. It is shown that it converges better than these techniques.
 Title
 Recurrent neural network approach for partitioning irregular graphs
 Book Title
 HighPerformance Computing and Networking
 Book Subtitle
 7th International Conference, HPCN Europe 1999 Amsterdam, The Netherlands, April 12–14, 1999 Proceedings
 Pages
 pp 450459
 Copyright
 1999
 DOI
 10.1007/BFb0100606
 Print ISBN
 9783540658214
 Online ISBN
 9783540489337
 Series Title
 Lecture Notes in Computer Science
 Series Volume
 1593
 Series ISSN
 03029743
 Publisher
 Springer Berlin Heidelberg
 Copyright Holder
 SpringerVerlag
 Additional Links
 Topics
 Industry Sectors
 eBook Packages
 Editors
 Authors

 MTahar Kechadi ^{(1)}
 Author Affiliations

 1. Parallel Computational Research Group, Department of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland
Continue reading...
To view the rest of this content please follow the download PDF link above.