Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Teachers and Classes with Neural Networks

Gislén, Lars LU ; Peterson, Carsten LU and Söderberg, Bo LU (1989) In International Journal of Neural Systems 1(2). p.167-176
Abstract
A convenient mapping and an efficient algorithm for solving scheduling problems within the neural network paradigm is presented. It is based on a reduced encoding scheme and a mean field annealing prescription which was recently successfully applied to TSP.

Most scheduling problems are characterized by a set of hard and soft constraints. The prime target of this work is the hard constraints. In this domain the algorithm persistently finds legal solutions for quite difficult problems. We also make some exploratory investigations by adding soft constraints with very encouraging results. Our numerical studies cover problem sizes up to O(105) degrees of freedom with no parameter tuning.

We stress the importance of adding... (More)
A convenient mapping and an efficient algorithm for solving scheduling problems within the neural network paradigm is presented. It is based on a reduced encoding scheme and a mean field annealing prescription which was recently successfully applied to TSP.

Most scheduling problems are characterized by a set of hard and soft constraints. The prime target of this work is the hard constraints. In this domain the algorithm persistently finds legal solutions for quite difficult problems. We also make some exploratory investigations by adding soft constraints with very encouraging results. Our numerical studies cover problem sizes up to O(105) degrees of freedom with no parameter tuning.

We stress the importance of adding self-coupling terms to the energy functions which are redundant from the encoding point of view but beneficial when it comes to ignoring local minima and to stabilizing the good solutions in the annealing process. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
International Journal of Neural Systems
volume
1
issue
2
pages
10 pages
publisher
World Scientific Publishing
ISSN
0129-0657
DOI
10.1142/S0129065789000074
language
English
LU publication?
yes
id
57eb8250-130a-4196-bd4e-ffe35b406203
date added to LUP
2019-05-13 19:36:03
date last changed
2025-04-04 15:03:21
@article{57eb8250-130a-4196-bd4e-ffe35b406203,
  abstract     = {{A convenient mapping and an efficient algorithm for solving scheduling problems within the neural network paradigm is presented. It is based on a reduced encoding scheme and a mean field annealing prescription which was recently successfully applied to TSP.<br/><br/>Most scheduling problems are characterized by a set of hard and soft constraints. The prime target of this work is the hard constraints. In this domain the algorithm persistently finds legal solutions for quite difficult problems. We also make some exploratory investigations by adding soft constraints with very encouraging results. Our numerical studies cover problem sizes up to O(105) degrees of freedom with no parameter tuning.<br/><br/>We stress the importance of adding self-coupling terms to the energy functions which are redundant from the encoding point of view but beneficial when it comes to ignoring local minima and to stabilizing the good solutions in the annealing process.}},
  author       = {{Gislén, Lars and Peterson, Carsten and Söderberg, Bo}},
  issn         = {{0129-0657}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{167--176}},
  publisher    = {{World Scientific Publishing}},
  series       = {{International Journal of Neural Systems}},
  title        = {{Teachers and Classes with Neural Networks}},
  url          = {{http://dx.doi.org/10.1142/S0129065789000074}},
  doi          = {{10.1142/S0129065789000074}},
  volume       = {{1}},
  year         = {{1989}},
}