Article for analog vector algebra computation

Allen P. Mills; Bernard Yurke; Philip M. Platzman

doi:10.1016/S0303-2647(99)00044-1

Article for analog vector algebra computation

Allen P. Mills, Bernard Yurke, Philip M. Platzman

Nokia

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

34 Scopus citations

Abstract

We introduce the concept of an analog neural network represented by chemical operations performed on strands of DNA. This new type of DNA computing has the advantage that it should be fault tolerant and thus more immune to DNA hybridization errors than a Boolean DNA computer. We describe a particular set of DNA operations to effect the interconversion of electrical and DNA data and to represent the Hopfield associative memory and the feed- forward neural network of Rumelhart et al. We speculate that networks containing as many as 10⁹ neurons might be feasible.

Original language	English
Pages (from-to)	175-180
Number of pages	6
Journal	BioSystems
Volume	52
Issue number	1-3
DOIs	https://doi.org/10.1016/S0303-2647(99)00044-1
State	Published - Oct 1999
Externally published	Yes

Keywords

DNA computing
Hopfield network
Neural networks

Access to Document

10.1016/S0303-2647(99)00044-1

Cite this

@article{7694fedada394381a862739949f75951,

title = "Article for analog vector algebra computation",

abstract = "We introduce the concept of an analog neural network represented by chemical operations performed on strands of DNA. This new type of DNA computing has the advantage that it should be fault tolerant and thus more immune to DNA hybridization errors than a Boolean DNA computer. We describe a particular set of DNA operations to effect the interconversion of electrical and DNA data and to represent the Hopfield associative memory and the feed- forward neural network of Rumelhart et al. We speculate that networks containing as many as 109 neurons might be feasible.",

keywords = "DNA computing, Hopfield network, Neural networks",

author = "Mills, {Allen P.} and Bernard Yurke and Platzman, {Philip M.}",

year = "1999",

month = oct,

doi = "10.1016/S0303-2647(99)00044-1",

language = "English",

volume = "52",

pages = "175--180",

journal = "BioSystems",

issn = "0303-2647",

publisher = "Elsevier Ireland Ltd",

number = "1-3",

}

TY - JOUR

T1 - Article for analog vector algebra computation

AU - Mills, Allen P.

AU - Yurke, Bernard

AU - Platzman, Philip M.

PY - 1999/10

Y1 - 1999/10

N2 - We introduce the concept of an analog neural network represented by chemical operations performed on strands of DNA. This new type of DNA computing has the advantage that it should be fault tolerant and thus more immune to DNA hybridization errors than a Boolean DNA computer. We describe a particular set of DNA operations to effect the interconversion of electrical and DNA data and to represent the Hopfield associative memory and the feed- forward neural network of Rumelhart et al. We speculate that networks containing as many as 109 neurons might be feasible.

AB - We introduce the concept of an analog neural network represented by chemical operations performed on strands of DNA. This new type of DNA computing has the advantage that it should be fault tolerant and thus more immune to DNA hybridization errors than a Boolean DNA computer. We describe a particular set of DNA operations to effect the interconversion of electrical and DNA data and to represent the Hopfield associative memory and the feed- forward neural network of Rumelhart et al. We speculate that networks containing as many as 109 neurons might be feasible.

KW - DNA computing

KW - Hopfield network

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=0345035350&partnerID=8YFLogxK

U2 - 10.1016/S0303-2647(99)00044-1

DO - 10.1016/S0303-2647(99)00044-1

M3 - Article

C2 - 10636042

AN - SCOPUS:0345035350

SN - 0303-2647

VL - 52

SP - 175

EP - 180

JO - BioSystems

JF - BioSystems

IS - 1-3

ER -

Article for analog vector algebra computation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this