The construction of minimal multilayered perceptrons : a case study for sorting

P.J. Zwietering, E.H.L. Aarts, J. Wessels

Research output: Contribution to journalArticleScientificpeer-review

Abstract

We consider the construction of minimal multilayered perceptrons for solving combinatorial optimization problems. Though general in nature, the proposed construction method is presented as a case study for the sorting problem. The presentation starts with an O((n!)2) three-layered perceptron based on complete enumeration, that solves the sorting problem of n numbers. This network is then gradually reduced to an O(n2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm.
Original languageEnglish
Pages (from-to)197-210
Number of pages14
JournalNeurocomputing
Volume5
Issue number4-5
DOIs
Publication statusPublished - 1993
Externally publishedYes

Fingerprint

Neural Networks (Computer)
Sorting
Neural networks
Combinatorial optimization

Cite this

Zwietering, P.J. ; Aarts, E.H.L. ; Wessels, J. / The construction of minimal multilayered perceptrons : a case study for sorting. In: Neurocomputing. 1993 ; Vol. 5, No. 4-5. pp. 197-210.
@article{5e757606e34640a39261dad0ad7fea0c,
title = "The construction of minimal multilayered perceptrons : a case study for sorting",
abstract = "We consider the construction of minimal multilayered perceptrons for solving combinatorial optimization problems. Though general in nature, the proposed construction method is presented as a case study for the sorting problem. The presentation starts with an O((n!)2) three-layered perceptron based on complete enumeration, that solves the sorting problem of n numbers. This network is then gradually reduced to an O(n2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm.",
author = "P.J. Zwietering and E.H.L. Aarts and J. Wessels",
year = "1993",
doi = "10.1016/0925-2312(93)90007-P",
language = "English",
volume = "5",
pages = "197--210",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier Science BV",
number = "4-5",

}

The construction of minimal multilayered perceptrons : a case study for sorting. / Zwietering, P.J.; Aarts, E.H.L.; Wessels, J.

In: Neurocomputing, Vol. 5, No. 4-5, 1993, p. 197-210.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - The construction of minimal multilayered perceptrons : a case study for sorting

AU - Zwietering, P.J.

AU - Aarts, E.H.L.

AU - Wessels, J.

PY - 1993

Y1 - 1993

N2 - We consider the construction of minimal multilayered perceptrons for solving combinatorial optimization problems. Though general in nature, the proposed construction method is presented as a case study for the sorting problem. The presentation starts with an O((n!)2) three-layered perceptron based on complete enumeration, that solves the sorting problem of n numbers. This network is then gradually reduced to an O(n2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm.

AB - We consider the construction of minimal multilayered perceptrons for solving combinatorial optimization problems. Though general in nature, the proposed construction method is presented as a case study for the sorting problem. The presentation starts with an O((n!)2) three-layered perceptron based on complete enumeration, that solves the sorting problem of n numbers. This network is then gradually reduced to an O(n2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm.

U2 - 10.1016/0925-2312(93)90007-P

DO - 10.1016/0925-2312(93)90007-P

M3 - Article

VL - 5

SP - 197

EP - 210

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 4-5

ER -