Ferroelectric thinfilm memory for electrically programmable ic neural networks

L. T. Clark, Sandwip Dey, R. O. Grondin

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

The application of ferroelectric thinfilm capacitors as connection element “synapses” in artificial neural network (ANN) integrated circuits (IC's) is described. A review of basic neural network structure, with an emphasis on electrical implementation in IC form is given. A binary (on/off efficacy) connection scheme of very high density is then described and analyzed. A continuous-valued synapse (analog memory) where the efficacy is controlled by the polarization of a ferroelectric capacitor element is then described. This analog synapse utilizes nondestructive readout and requires very infrequent refresh.

Original languageEnglish (US)
Pages (from-to)205-213
Number of pages9
JournalFerroelectrics
Volume116
Issue number1
DOIs
StatePublished - Jan 1 1991

Fingerprint

synapses
Ferroelectric materials
Integrated circuits
Capacitors
Neural networks
Data storage equipment
integrated circuits
capacitors
analogs
Polarization
readout
polarization

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Ferroelectric thinfilm memory for electrically programmable ic neural networks. / Clark, L. T.; Dey, Sandwip; Grondin, R. O.

In: Ferroelectrics, Vol. 116, No. 1, 01.01.1991, p. 205-213.

Research output: Contribution to journalArticle

Clark, L. T. ; Dey, Sandwip ; Grondin, R. O. / Ferroelectric thinfilm memory for electrically programmable ic neural networks. In: Ferroelectrics. 1991 ; Vol. 116, No. 1. pp. 205-213.
@article{cc2b2ad0c97249699c041a0efbaa6053,
title = "Ferroelectric thinfilm memory for electrically programmable ic neural networks",
abstract = "The application of ferroelectric thinfilm capacitors as connection element “synapses” in artificial neural network (ANN) integrated circuits (IC's) is described. A review of basic neural network structure, with an emphasis on electrical implementation in IC form is given. A binary (on/off efficacy) connection scheme of very high density is then described and analyzed. A continuous-valued synapse (analog memory) where the efficacy is controlled by the polarization of a ferroelectric capacitor element is then described. This analog synapse utilizes nondestructive readout and requires very infrequent refresh.",
author = "Clark, {L. T.} and Sandwip Dey and Grondin, {R. O.}",
year = "1991",
month = "1",
day = "1",
doi = "10.1080/00150199108007943",
language = "English (US)",
volume = "116",
pages = "205--213",
journal = "Ferroelectrics",
issn = "0015-0193",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Ferroelectric thinfilm memory for electrically programmable ic neural networks

AU - Clark, L. T.

AU - Dey, Sandwip

AU - Grondin, R. O.

PY - 1991/1/1

Y1 - 1991/1/1

N2 - The application of ferroelectric thinfilm capacitors as connection element “synapses” in artificial neural network (ANN) integrated circuits (IC's) is described. A review of basic neural network structure, with an emphasis on electrical implementation in IC form is given. A binary (on/off efficacy) connection scheme of very high density is then described and analyzed. A continuous-valued synapse (analog memory) where the efficacy is controlled by the polarization of a ferroelectric capacitor element is then described. This analog synapse utilizes nondestructive readout and requires very infrequent refresh.

AB - The application of ferroelectric thinfilm capacitors as connection element “synapses” in artificial neural network (ANN) integrated circuits (IC's) is described. A review of basic neural network structure, with an emphasis on electrical implementation in IC form is given. A binary (on/off efficacy) connection scheme of very high density is then described and analyzed. A continuous-valued synapse (analog memory) where the efficacy is controlled by the polarization of a ferroelectric capacitor element is then described. This analog synapse utilizes nondestructive readout and requires very infrequent refresh.

UR - http://www.scopus.com/inward/record.url?scp=84963120276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963120276&partnerID=8YFLogxK

U2 - 10.1080/00150199108007943

DO - 10.1080/00150199108007943

M3 - Article

AN - SCOPUS:84963120276

VL - 116

SP - 205

EP - 213

JO - Ferroelectrics

JF - Ferroelectrics

SN - 0015-0193

IS - 1

ER -