Integrated circuit neural networks using ferroelectric analog memory

Lawrence T Clark; R. O. Grondin; S. K. Dey

doi:10.1109/PCCC.1992.200514

Integrated circuit neural networks using ferroelectric analog memory

Lawrence T Clark, R. O. Grondin, S. K. Dey

Chemical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

The application of ferroelectric thin-film capacitors as synapses in integrated circuit implementation of artificial neural networks is described. A continuous-valued synapse where the synaptic efficacy is controlled by the polarization of a ferroelectric capacitor element is presented. The ferroelectric analog synapse utilizes nondestructive readout. A ferroelectric capacitor circuit model has been added to the SPICE circuit simulation program and is complete with respect to current vs. time, polarization, and current vs. voltage responses. The simulated response in characterization circuits is shown to closely model that of lead zirconate titanate (PZT) thin-film capacitors. Simulation and experimental results show the proposed synapse circuit to possess a number of favorable characteristics, including very infrequent refresh and fine programming granularity.

Original language	English (US)
Title of host publication	11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	736-742
Number of pages	7
ISBN (Electronic)	0780306058, 9780780306059
DOIs	https://doi.org/10.1109/PCCC.1992.200514
State	Published - 1992
Event	11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Scottsdale, United States Duration: Apr 1 1992 → Apr 3 1992

Publication series

Name	11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings

Conference

Conference	11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992
Country/Territory	United States
City	Scottsdale
Period	4/1/92 → 4/3/92

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Hardware and Architecture
Information Systems and Management

Access to Document

10.1109/PCCC.1992.200514

Cite this

Clark, L. T., Grondin, R. O., & Dey, S. K. (1992). Integrated circuit neural networks using ferroelectric analog memory. In 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings (pp. 736-742). Article 200514 (11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PCCC.1992.200514

Integrated circuit neural networks using ferroelectric analog memory. / Clark, Lawrence T; Grondin, R. O.; Dey, S. K.
11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 1992. p. 736-742 200514 (11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Clark, LT, Grondin, RO & Dey, SK 1992, Integrated circuit neural networks using ferroelectric analog memory. in 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings., 200514, 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 736-742, 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992, Scottsdale, United States, 4/1/92. https://doi.org/10.1109/PCCC.1992.200514

Clark LT, Grondin RO, Dey SK. Integrated circuit neural networks using ferroelectric analog memory. In 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 1992. p. 736-742. 200514. (11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings). doi: 10.1109/PCCC.1992.200514

Clark, Lawrence T ; Grondin, R. O. ; Dey, S. K. / Integrated circuit neural networks using ferroelectric analog memory. 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 1992. pp. 736-742 (11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings).

@inproceedings{c716c6bba3dc41eb8e05d200b7bb72be,

title = "Integrated circuit neural networks using ferroelectric analog memory",

abstract = "The application of ferroelectric thin-film capacitors as synapses in integrated circuit implementation of artificial neural networks is described. A continuous-valued synapse where the synaptic efficacy is controlled by the polarization of a ferroelectric capacitor element is presented. The ferroelectric analog synapse utilizes nondestructive readout. A ferroelectric capacitor circuit model has been added to the SPICE circuit simulation program and is complete with respect to current vs. time, polarization, and current vs. voltage responses. The simulated response in characterization circuits is shown to closely model that of lead zirconate titanate (PZT) thin-film capacitors. Simulation and experimental results show the proposed synapse circuit to possess a number of favorable characteristics, including very infrequent refresh and fine programming granularity.",

author = "Clark, {Lawrence T} and Grondin, {R. O.} and Dey, {S. K.}",

note = "Publisher Copyright: {\textcopyright} 1992 IEEE.; 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 ; Conference date: 01-04-1992 Through 03-04-1992",

year = "1992",

doi = "10.1109/PCCC.1992.200514",

language = "English (US)",

series = "11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "736--742",

booktitle = "11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings",

}

TY - GEN

T1 - Integrated circuit neural networks using ferroelectric analog memory

AU - Clark, Lawrence T

AU - Grondin, R. O.

AU - Dey, S. K.

PY - 1992

Y1 - 1992

N2 - The application of ferroelectric thin-film capacitors as synapses in integrated circuit implementation of artificial neural networks is described. A continuous-valued synapse where the synaptic efficacy is controlled by the polarization of a ferroelectric capacitor element is presented. The ferroelectric analog synapse utilizes nondestructive readout. A ferroelectric capacitor circuit model has been added to the SPICE circuit simulation program and is complete with respect to current vs. time, polarization, and current vs. voltage responses. The simulated response in characterization circuits is shown to closely model that of lead zirconate titanate (PZT) thin-film capacitors. Simulation and experimental results show the proposed synapse circuit to possess a number of favorable characteristics, including very infrequent refresh and fine programming granularity.

AB - The application of ferroelectric thin-film capacitors as synapses in integrated circuit implementation of artificial neural networks is described. A continuous-valued synapse where the synaptic efficacy is controlled by the polarization of a ferroelectric capacitor element is presented. The ferroelectric analog synapse utilizes nondestructive readout. A ferroelectric capacitor circuit model has been added to the SPICE circuit simulation program and is complete with respect to current vs. time, polarization, and current vs. voltage responses. The simulated response in characterization circuits is shown to closely model that of lead zirconate titanate (PZT) thin-film capacitors. Simulation and experimental results show the proposed synapse circuit to possess a number of favorable characteristics, including very infrequent refresh and fine programming granularity.

UR - http://www.scopus.com/inward/record.url?scp=84950032320&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84950032320&partnerID=8YFLogxK

U2 - 10.1109/PCCC.1992.200514

DO - 10.1109/PCCC.1992.200514

M3 - Conference contribution

AN - SCOPUS:84950032320

T3 - 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings

SP - 736

EP - 742

BT - 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th Annual International Phoenix Conference on Computers and Communication, IPCCC 1992

Y2 - 1 April 1992 through 3 April 1992

ER -

Integrated circuit neural networks using ferroelectric analog memory

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this