Boltzmann machines as a model for parallel annealing

E.H.L. Aarts; J.H.M. Korst

doi:10.1007/BF01759053

Boltzmann machines as a model for parallel annealing

Research output: Contribution to journal › Article › Scientific › peer-review

Abstract

The potential of Boltzmann machines to cope with difficult combinatorial optimization problems is investigated. A discussion of various (parallel) models of Boltzmann machines is given based on the theory of Markov chains. A general strategy is presented for solving (approximately) combinatorial optimization problems with a Boltzmann machine. The strategy is illustrated by discussing the details for two different problems, namely MATCHING and GRAPH PARTITIONING.

Original language	English
Pages (from-to)	437-465
Number of pages	29
Journal	Algorithmica
Volume	6
Issue number	3
DOIs	https://doi.org/10.1007/BF01759053
Publication status	Published - 1991
Externally published	Yes

Access to Document

10.1007/BF01759053

Cite this

@article{945ec50ca8a641ac995cbc445cccd0a8,

title = "Boltzmann machines as a model for parallel annealing",

abstract = "The potential of Boltzmann machines to cope with difficult combinatorial optimization problems is investigated. A discussion of various (parallel) models of Boltzmann machines is given based on the theory of Markov chains. A general strategy is presented for solving (approximately) combinatorial optimization problems with a Boltzmann machine. The strategy is illustrated by discussing the details for two different problems, namely MATCHING and GRAPH PARTITIONING.",

author = "E.H.L. Aarts and J.H.M. Korst",

year = "1991",

doi = "10.1007/BF01759053",

language = "English",

volume = "6",

pages = "437--465",

journal = "Algorithmica",

issn = "0178-4617",

publisher = "Springer New York",

number = "3",

}

TY - JOUR

T1 - Boltzmann machines as a model for parallel annealing

AU - Aarts, E.H.L.

AU - Korst, J.H.M.

PY - 1991

Y1 - 1991

N2 - The potential of Boltzmann machines to cope with difficult combinatorial optimization problems is investigated. A discussion of various (parallel) models of Boltzmann machines is given based on the theory of Markov chains. A general strategy is presented for solving (approximately) combinatorial optimization problems with a Boltzmann machine. The strategy is illustrated by discussing the details for two different problems, namely MATCHING and GRAPH PARTITIONING.

AB - The potential of Boltzmann machines to cope with difficult combinatorial optimization problems is investigated. A discussion of various (parallel) models of Boltzmann machines is given based on the theory of Markov chains. A general strategy is presented for solving (approximately) combinatorial optimization problems with a Boltzmann machine. The strategy is illustrated by discussing the details for two different problems, namely MATCHING and GRAPH PARTITIONING.

U2 - 10.1007/BF01759053

DO - 10.1007/BF01759053

M3 - Article

SN - 0178-4617

VL - 6

SP - 437

EP - 465

JO - Algorithmica

JF - Algorithmica

IS - 3

ER -

Boltzmann machines as a model for parallel annealing

Abstract

Access to Document

Fingerprint

Cite this