Ferroelectric connections for IC neural networks

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

There has been a great deal of interest in producing integrated circuit devices which implement artificial neural networks (ANN) directly as analog circuits. The development of very dense connection schemes which allow electrical control of the connection efficacy would be very beneficial to such implementations. This paper will report on the use of ferroelectric thin-films in such connection elements. These may be fabricated using thin-film deposition techniques above the CMOS circuitry imposing little space penalty. Specifically, we report on two different connection schemes. The first will support binary weighted connections, while the second will support continuous-valued weights and promises non-volatile operation.

Original languageEnglish (US)
Title of host publicationIEE Conference Publication
PublisherPubl by IEE
Pages47-51
Number of pages5
Edition313
StatePublished - 1989
EventFirst IEE International Conference on Artificial Neural Networks - London, Engl
Duration: Oct 16 1989Oct 18 1989

Other

OtherFirst IEE International Conference on Artificial Neural Networks
CityLondon, Engl
Period10/16/8910/18/89

Fingerprint

Ferroelectric thin films
Analog circuits
Ferroelectric materials
Integrated circuits
Neural networks
Thin films

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Clark, L. T., Grondin, R. O., & Dey, S. (1989). Ferroelectric connections for IC neural networks. In IEE Conference Publication (313 ed., pp. 47-51). Publ by IEE.

Ferroelectric connections for IC neural networks. / Clark, L. T.; Grondin, R. O.; Dey, Sandwip.

IEE Conference Publication. 313. ed. Publ by IEE, 1989. p. 47-51.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Clark, LT, Grondin, RO & Dey, S 1989, Ferroelectric connections for IC neural networks. in IEE Conference Publication. 313 edn, Publ by IEE, pp. 47-51, First IEE International Conference on Artificial Neural Networks, London, Engl, 10/16/89.
Clark LT, Grondin RO, Dey S. Ferroelectric connections for IC neural networks. In IEE Conference Publication. 313 ed. Publ by IEE. 1989. p. 47-51
Clark, L. T. ; Grondin, R. O. ; Dey, Sandwip. / Ferroelectric connections for IC neural networks. IEE Conference Publication. 313. ed. Publ by IEE, 1989. pp. 47-51
@inproceedings{d3adfd6aba394a86b892691dcefeca3a,
title = "Ferroelectric connections for IC neural networks",
abstract = "There has been a great deal of interest in producing integrated circuit devices which implement artificial neural networks (ANN) directly as analog circuits. The development of very dense connection schemes which allow electrical control of the connection efficacy would be very beneficial to such implementations. This paper will report on the use of ferroelectric thin-films in such connection elements. These may be fabricated using thin-film deposition techniques above the CMOS circuitry imposing little space penalty. Specifically, we report on two different connection schemes. The first will support binary weighted connections, while the second will support continuous-valued weights and promises non-volatile operation.",
author = "Clark, {L. T.} and Grondin, {R. O.} and Sandwip Dey",
year = "1989",
language = "English (US)",
pages = "47--51",
booktitle = "IEE Conference Publication",
publisher = "Publ by IEE",
edition = "313",

}

TY - GEN

T1 - Ferroelectric connections for IC neural networks

AU - Clark, L. T.

AU - Grondin, R. O.

AU - Dey, Sandwip

PY - 1989

Y1 - 1989

N2 - There has been a great deal of interest in producing integrated circuit devices which implement artificial neural networks (ANN) directly as analog circuits. The development of very dense connection schemes which allow electrical control of the connection efficacy would be very beneficial to such implementations. This paper will report on the use of ferroelectric thin-films in such connection elements. These may be fabricated using thin-film deposition techniques above the CMOS circuitry imposing little space penalty. Specifically, we report on two different connection schemes. The first will support binary weighted connections, while the second will support continuous-valued weights and promises non-volatile operation.

AB - There has been a great deal of interest in producing integrated circuit devices which implement artificial neural networks (ANN) directly as analog circuits. The development of very dense connection schemes which allow electrical control of the connection efficacy would be very beneficial to such implementations. This paper will report on the use of ferroelectric thin-films in such connection elements. These may be fabricated using thin-film deposition techniques above the CMOS circuitry imposing little space penalty. Specifically, we report on two different connection schemes. The first will support binary weighted connections, while the second will support continuous-valued weights and promises non-volatile operation.

UR - http://www.scopus.com/inward/record.url?scp=0024933128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024933128&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024933128

SP - 47

EP - 51

BT - IEE Conference Publication

PB - Publ by IEE

ER -