Ferroelectric connections for IC neural networks

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

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

3 Scopus citations

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

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Ferroelectric connections for IC neural networks'. Together they form a unique fingerprint.

Cite this