Deep Learning Approach to Modeling and Exploring Random Sources of Gate-All-Around Silicon Nanosheet MOSFETs

Rajat Butola, Yiming Li*, Sekhar Reddy Kola

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

In this paper, for the first time, deep learning (DL) based artificial neural network (ANN) is applied to model the effects of various random variations: work function fluctuation, random dopant fluctuation, and interface trap fluctuation, on gate-all-around silicon nanosheet MOSFETs. The number of fluctuations for each source variation is used as input features and their effects on devices of interest are studied qualitatively and quantitatively. The key figures of merit (FoM) are also extracted accurately from the transfer characteristics, which shows the competency of the ANN model in the domain of device modeling.

Original languageEnglish
Title of host publication2022 International Symposium on VLSI Technology, Systems and Applications, VLSI-TSA 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665409230
DOIs
StatePublished - 2022
Event2022 International Symposium on VLSI Technology, Systems and Applications, VLSI-TSA 2022 - Hsinchu, Taiwan
Duration: 18 Apr 202221 Apr 2022

Publication series

Name2022 International Symposium on VLSI Technology, Systems and Applications, VLSI-TSA 2022

Conference

Conference2022 International Symposium on VLSI Technology, Systems and Applications, VLSI-TSA 2022
Country/TerritoryTaiwan
CityHsinchu
Period18/04/2221/04/22

Fingerprint

Dive into the research topics of 'Deep Learning Approach to Modeling and Exploring Random Sources of Gate-All-Around Silicon Nanosheet MOSFETs'. Together they form a unique fingerprint.

Cite this