Sorting with a neural net

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

Sorting with a neural net

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

Research output: Book/Report › Book › Scientific

Abstract

In this paper a three-layered perceptron is derived that exactly solves the problem of sorting n numbers. The perceptron configuration has O(n^2) nodes and can be viewed as a "neural" implementation of the parallel enumerative sorting algorithm developed by Preparata. Furthermore, it is shown that the problem of sorting n numbers cannot be solved exactly by a two-layered perceptron. Keywords: Sorting, Combinatorial Optimization, Neural Network, Multi-Layered Perceptron, Classification.

Original language	English
Place of Publication	Eindhoven
Publisher	Technische Universiteit Eindhoven
Publication status	Published - 1991
Externally published	Yes

Publication series

Name	Memorandum COSOR

Cite this

@book{11dbbb84af6548418358fce296bd9893,

title = "Sorting with a neural net",

abstract = "In this paper a three-layered perceptron is derived that exactly solves the problem of sorting n numbers. The perceptron configuration has O(n^2) nodes and can be viewed as a {"}neural{"} implementation of the parallel enumerative sorting algorithm developed by Preparata. Furthermore, it is shown that the problem of sorting n numbers cannot be solved exactly by a two-layered perceptron. Keywords: Sorting, Combinatorial Optimization, Neural Network, Multi-Layered Perceptron, Classification.",

author = "P.J. Zwietering and E.H.L. Aarts and J. Wessels",

year = "1991",

language = "English",

series = "Memorandum COSOR",

publisher = "Technische Universiteit Eindhoven",

}

TY - BOOK

T1 - Sorting with a neural net

AU - Zwietering, P.J.

AU - Aarts, E.H.L.

AU - Wessels, J.

PY - 1991

Y1 - 1991

N2 - In this paper a three-layered perceptron is derived that exactly solves the problem of sorting n numbers. The perceptron configuration has O(n^2) nodes and can be viewed as a "neural" implementation of the parallel enumerative sorting algorithm developed by Preparata. Furthermore, it is shown that the problem of sorting n numbers cannot be solved exactly by a two-layered perceptron. Keywords: Sorting, Combinatorial Optimization, Neural Network, Multi-Layered Perceptron, Classification.

AB - In this paper a three-layered perceptron is derived that exactly solves the problem of sorting n numbers. The perceptron configuration has O(n^2) nodes and can be viewed as a "neural" implementation of the parallel enumerative sorting algorithm developed by Preparata. Furthermore, it is shown that the problem of sorting n numbers cannot be solved exactly by a two-layered perceptron. Keywords: Sorting, Combinatorial Optimization, Neural Network, Multi-Layered Perceptron, Classification.

M3 - Book

T3 - Memorandum COSOR

BT - Sorting with a neural net

PB - Technische Universiteit Eindhoven

CY - Eindhoven

ER -

Sorting with a neural net

Abstract

Publication series

Fingerprint

Cite this