Integrated circuit neural networks using ferroelectric analog memory

Author

Clark, Lawrene T. ; Grondin, Robert O. ; Dey, Sandwip K.

Author_Institution

Arizona State Univ., Tempe, AZ, USA

fYear

1992

fDate

1-3 April 1992

Firstpage

736

Lastpage

742

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.<>

Keywords

artificial intelligence; circuit analysis computing; ferroelectric thin films; monolithic integrated circuits; neural nets; thin film capacitors; SPICE circuit simulation program; artificial neural networks; ferroelectric analog memory; ferroelectric thin-film capacitors; fine programming granularity; integrated circuit neural networks; nondestructive readout; synapses; Analog integrated circuits; Application specific integrated circuits; Artificial neural networks; Capacitors; Circuit simulation; Ferroelectric materials; Neural networks; Polarization; SPICE; Thin film circuits;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers and Communications, 1992. Conference Proceedings., Eleventh Annual International Phoenix Conference on

Conference_Location

Scottsdale, AZ, USA

Print_ISBN

0-7803-0605-8

Type

conf

DOI

10.1109/PCCC.1992.200514

Filename

200514