The construction of minimal multi-layered perceptrons : a case study for sorting

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

Research output: Book/ReportBookScientific

Abstract

We consider the construction of minimal multi-layered perceptrons for solving combinatorial optimization problems. Though general in nature, the 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(n^2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm. Key words: minimal multi-layered percept1'Ons, feed-forward neural networks, combinatorial optimization problems, sorting.
Original languageEnglish
Place of PublicationEindhoven
PublisherTechnische Universiteit Eindhoven
Publication statusPublished - 1992
Externally publishedYes

Publication series

NameMemorandum COSOR

Fingerprint

Sorting
Neural networks
Combinatorial optimization
Feedforward neural networks

Cite this

Zwietering, P. J., Aarts, E. H. L., & Wessels, J. (1992). The construction of minimal multi-layered perceptrons : a case study for sorting. (Memorandum COSOR). Eindhoven: Technische Universiteit Eindhoven.
Zwietering, P.J. ; Aarts, E.H.L. ; Wessels, J. / The construction of minimal multi-layered perceptrons : a case study for sorting. Eindhoven : Technische Universiteit Eindhoven, 1992. (Memorandum COSOR).
@book{3f550ad519a04333ba8148494a0fa73c,
title = "The construction of minimal multi-layered perceptrons : a case study for sorting",
abstract = "We consider the construction of minimal multi-layered perceptrons for solving combinatorial optimization problems. Though general in nature, the 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(n^2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm. Key words: minimal multi-layered percept1'Ons, feed-forward neural networks, combinatorial optimization problems, sorting.",
author = "P.J. Zwietering and E.H.L. Aarts and J. Wessels",
year = "1992",
language = "English",
series = "Memorandum COSOR",
publisher = "Technische Universiteit Eindhoven",

}

Zwietering, PJ, Aarts, EHL & Wessels, J 1992, The construction of minimal multi-layered perceptrons : a case study for sorting. Memorandum COSOR, Technische Universiteit Eindhoven, Eindhoven.

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

Eindhoven : Technische Universiteit Eindhoven, 1992. (Memorandum COSOR).

Research output: Book/ReportBookScientific

TY - BOOK

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

AU - Zwietering, P.J.

AU - Aarts, E.H.L.

AU - Wessels, J.

PY - 1992

Y1 - 1992

N2 - We consider the construction of minimal multi-layered perceptrons for solving combinatorial optimization problems. Though general in nature, the 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(n^2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm. Key words: minimal multi-layered percept1'Ons, feed-forward neural networks, combinatorial optimization problems, sorting.

AB - We consider the construction of minimal multi-layered perceptrons for solving combinatorial optimization problems. Though general in nature, the 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(n^2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm. Key words: minimal multi-layered percept1'Ons, feed-forward neural networks, combinatorial optimization problems, sorting.

M3 - Book

T3 - Memorandum COSOR

BT - The construction of minimal multi-layered perceptrons : a case study for sorting

PB - Technische Universiteit Eindhoven

CY - Eindhoven

ER -

Zwietering PJ, Aarts EHL, Wessels J. The construction of minimal multi-layered perceptrons : a case study for sorting. Eindhoven: Technische Universiteit Eindhoven, 1992. (Memorandum COSOR).