OPTICAL IMPLEMENTATIONS IN BOLTZMANN MACHINES.

Anthony J. Ticknor; Harrison Barrett

doi:10.1117/12.7974015

OPTICAL IMPLEMENTATIONS IN BOLTZMANN MACHINES.

Anthony J. Ticknor, Harrison Barrett

Medical Imaging

Research output: Contribution to journal › Article

20 Scopus citations

Abstract

Boltzmann machines can be used to obtain solutions to problems for which direct mathematical calculation of a solution is not possible or would take too long. The range of problems for which such a machine might be useful is very broad, and inversion of a linear equation is described as one example. A method is described that allows time-intensive operations on a computer to be replaced with a highly parallel optical system that can be incorporated in such a way as to let the computer take full advantage of the speed of the optics without sacrificing the precision possible in the computer. A tie is made between Boltzmann machines and neural networks, and it is shown how a Boltzmann machine may perform functions demonstrated by other neural network architectures.

Original language	English (US)
Pages (from-to)	16-21
Number of pages	6
Journal	Optical Engineering
Volume	26
Issue number	1
DOIs	https://doi.org/10.1117/12.7974015
State	Published - Jan 1 1987

ASJC Scopus subject areas

Atomic and Molecular Physics, and Optics
Engineering(all)

Access to Document

10.1117/12.7974015

Fingerprint Dive into the research topics of 'OPTICAL IMPLEMENTATIONS IN BOLTZMANN MACHINES.'. Together they form a unique fingerprint.

Cite this

Ticknor, A. J., & Barrett, H. (1987). OPTICAL IMPLEMENTATIONS IN BOLTZMANN MACHINES. Optical Engineering, 26(1), 16-21. https://doi.org/10.1117/12.7974015

@article{d468d8b2d04f4871993265738c8da266,

title = "OPTICAL IMPLEMENTATIONS IN BOLTZMANN MACHINES.",

abstract = "Boltzmann machines can be used to obtain solutions to problems for which direct mathematical calculation of a solution is not possible or would take too long. The range of problems for which such a machine might be useful is very broad, and inversion of a linear equation is described as one example. A method is described that allows time-intensive operations on a computer to be replaced with a highly parallel optical system that can be incorporated in such a way as to let the computer take full advantage of the speed of the optics without sacrificing the precision possible in the computer. A tie is made between Boltzmann machines and neural networks, and it is shown how a Boltzmann machine may perform functions demonstrated by other neural network architectures.",

author = "Ticknor, {Anthony J.} and Harrison Barrett",

year = "1987",

month = jan,

day = "1",

doi = "10.1117/12.7974015",

language = "English (US)",

volume = "26",

pages = "16--21",

journal = "Optical Engineering",

issn = "0091-3286",

publisher = "SPIE",

number = "1",

}

TY - JOUR

T1 - OPTICAL IMPLEMENTATIONS IN BOLTZMANN MACHINES.

AU - Ticknor, Anthony J.

AU - Barrett, Harrison

PY - 1987/1/1

Y1 - 1987/1/1

N2 - Boltzmann machines can be used to obtain solutions to problems for which direct mathematical calculation of a solution is not possible or would take too long. The range of problems for which such a machine might be useful is very broad, and inversion of a linear equation is described as one example. A method is described that allows time-intensive operations on a computer to be replaced with a highly parallel optical system that can be incorporated in such a way as to let the computer take full advantage of the speed of the optics without sacrificing the precision possible in the computer. A tie is made between Boltzmann machines and neural networks, and it is shown how a Boltzmann machine may perform functions demonstrated by other neural network architectures.

AB - Boltzmann machines can be used to obtain solutions to problems for which direct mathematical calculation of a solution is not possible or would take too long. The range of problems for which such a machine might be useful is very broad, and inversion of a linear equation is described as one example. A method is described that allows time-intensive operations on a computer to be replaced with a highly parallel optical system that can be incorporated in such a way as to let the computer take full advantage of the speed of the optics without sacrificing the precision possible in the computer. A tie is made between Boltzmann machines and neural networks, and it is shown how a Boltzmann machine may perform functions demonstrated by other neural network architectures.

UR - http://www.scopus.com/inward/record.url?scp=0023123199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023123199&partnerID=8YFLogxK

U2 - 10.1117/12.7974015

DO - 10.1117/12.7974015

M3 - Article

AN - SCOPUS:0023123199

VL - 26

SP - 16

EP - 21

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 1

ER -