The convergence of parallel Boltzmann machines

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

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

Abstract

We discuss the main results obtained in a study of a mathematical model of synchronously parallel Boltzmann machines. We present supporting evidence for the conjecture that a synchronously parallel Boltzmann machine maximizes a consensus function that consists of a weighted sum of the regular consensus function and a pseudo consensus function. The weighting is determined by the fraction of units that can change their states simultaneously.
Original languageEnglish
Title of host publicationParallel Processing in Neural Systems and Computers
Place of PublicationAmsterdam
PublisherElsevier
Pages277-280
Number of pages4
ISBN (Print)0-444-88390-8
Publication statusPublished - 1990
Externally publishedYes

Fingerprint

Boltzmann Machine
Weighted Sums
Weighting
Maximise
Mathematical Model
Unit

Cite this

Zwietering, P. J., & Aarts, E. H. L. (1990). The convergence of parallel Boltzmann machines. In Parallel Processing in Neural Systems and Computers (pp. 277-280). Amsterdam: Elsevier.
Zwietering, P.J. ; Aarts, E.H.L. / The convergence of parallel Boltzmann machines. Parallel Processing in Neural Systems and Computers. Amsterdam : Elsevier, 1990. pp. 277-280
@inbook{b5ef8954c7174867a69a16c7e9e4e54d,
title = "The convergence of parallel Boltzmann machines",
abstract = "We discuss the main results obtained in a study of a mathematical model of synchronously parallel Boltzmann machines. We present supporting evidence for the conjecture that a synchronously parallel Boltzmann machine maximizes a consensus function that consists of a weighted sum of the regular consensus function and a pseudo consensus function. The weighting is determined by the fraction of units that can change their states simultaneously.",
author = "P.J. Zwietering and E.H.L. Aarts",
year = "1990",
language = "English",
isbn = "0-444-88390-8",
pages = "277--280",
booktitle = "Parallel Processing in Neural Systems and Computers",
publisher = "Elsevier",
address = "Netherlands",

}

Zwietering, PJ & Aarts, EHL 1990, The convergence of parallel Boltzmann machines. in Parallel Processing in Neural Systems and Computers. Elsevier, Amsterdam, pp. 277-280.

The convergence of parallel Boltzmann machines. / Zwietering, P.J.; Aarts, E.H.L.

Parallel Processing in Neural Systems and Computers. Amsterdam : Elsevier, 1990. p. 277-280.

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

TY - CHAP

T1 - The convergence of parallel Boltzmann machines

AU - Zwietering, P.J.

AU - Aarts, E.H.L.

PY - 1990

Y1 - 1990

N2 - We discuss the main results obtained in a study of a mathematical model of synchronously parallel Boltzmann machines. We present supporting evidence for the conjecture that a synchronously parallel Boltzmann machine maximizes a consensus function that consists of a weighted sum of the regular consensus function and a pseudo consensus function. The weighting is determined by the fraction of units that can change their states simultaneously.

AB - We discuss the main results obtained in a study of a mathematical model of synchronously parallel Boltzmann machines. We present supporting evidence for the conjecture that a synchronously parallel Boltzmann machine maximizes a consensus function that consists of a weighted sum of the regular consensus function and a pseudo consensus function. The weighting is determined by the fraction of units that can change their states simultaneously.

M3 - Chapter

SN - 0-444-88390-8

SP - 277

EP - 280

BT - Parallel Processing in Neural Systems and Computers

PB - Elsevier

CY - Amsterdam

ER -

Zwietering PJ, Aarts EHL. The convergence of parallel Boltzmann machines. In Parallel Processing in Neural Systems and Computers. Amsterdam: Elsevier. 1990. p. 277-280