Parallel Boltzmann machines : a mathematical model

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

doi:10.1016/0743-7315(91)90110-U

Parallel Boltzmann machines : a mathematical model

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

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

1 Citation (Scopus)

Abstract

A mathematical model is presented for the description of parallel Boltzmann machines. The framework is based on the theory of Markov chains and combines a number of previously known results into one generic model. It is argued that parallel Boltzmann machines maximize a function consisting of a weighted sum of the well-known consensus function and a pseudoconsensus function. The weighting is determined by the amount of parallelism used in the Boltzmann machine and turns out to be problem dependent.

Original language	English
Pages (from-to)	65-75
Number of pages	11
Journal	Journal of Parallel and Distributed Computing
Volume	13
Issue number	1
DOIs	https://doi.org/10.1016/0743-7315(91)90110-U
Publication status	Published - 1991
Externally published	Yes

Access to Document

10.1016/0743-7315(91)90110-U

Cite this

@article{7f294ba6d74b4b15ae39d146bc7724e5,

title = "Parallel Boltzmann machines : a mathematical model",

abstract = "A mathematical model is presented for the description of parallel Boltzmann machines. The framework is based on the theory of Markov chains and combines a number of previously known results into one generic model. It is argued that parallel Boltzmann machines maximize a function consisting of a weighted sum of the well-known consensus function and a pseudoconsensus function. The weighting is determined by the amount of parallelism used in the Boltzmann machine and turns out to be problem dependent.",

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

year = "1991",

doi = "10.1016/0743-7315(91)90110-U",

language = "English",

volume = "13",

pages = "65--75",

journal = "Journal of Parallel and Distributed Computing",

issn = "0743-7315",

publisher = "Academic Press Inc.",

number = "1",

}

TY - JOUR

T1 - Parallel Boltzmann machines : a mathematical model

AU - Zwietering, P.J.

AU - Aarts, E.H.L.

PY - 1991

Y1 - 1991

N2 - A mathematical model is presented for the description of parallel Boltzmann machines. The framework is based on the theory of Markov chains and combines a number of previously known results into one generic model. It is argued that parallel Boltzmann machines maximize a function consisting of a weighted sum of the well-known consensus function and a pseudoconsensus function. The weighting is determined by the amount of parallelism used in the Boltzmann machine and turns out to be problem dependent.

AB - A mathematical model is presented for the description of parallel Boltzmann machines. The framework is based on the theory of Markov chains and combines a number of previously known results into one generic model. It is argued that parallel Boltzmann machines maximize a function consisting of a weighted sum of the well-known consensus function and a pseudoconsensus function. The weighting is determined by the amount of parallelism used in the Boltzmann machine and turns out to be problem dependent.

U2 - 10.1016/0743-7315(91)90110-U

DO - 10.1016/0743-7315(91)90110-U

M3 - Article

SN - 0743-7315

VL - 13

SP - 65

EP - 75

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

IS - 1

ER -

Parallel Boltzmann machines : a mathematical model

Abstract

Access to Document

Fingerprint

Cite this