DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Bokyeom | ko |
dc.contributor.author | Shin, Mincheol | ko |
dc.date.accessioned | 2023-11-16T02:00:41Z | - |
dc.date.available | 2023-11-16T02:00:41Z | - |
dc.date.created | 2023-11-06 | - |
dc.date.issued | 2023-11 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON ELECTRON DEVICES, v.70, no.11, pp.6021 - 6025 | - |
dc.identifier.issn | 0018-9383 | - |
dc.identifier.uri | http://hdl.handle.net/10203/314748 | - |
dc.description.abstract | In this work, we present a novel physics-informed machine learning (PIML)-based neural-network device modeling that predicts both device performance and spatial physical quantities in real-time. Using cutting-edge technologies such as physics-informed neural network (NN) and physics-informed deep operator networks, our approach suggests interpolation and extrapolation strategies in device physics modeling. Despite being trained with a small number of bias voltages, our model demonstrates remarkable accuracy, with a mean absolute percentage error (MAPE) of 0.12% for predicting potential for interpolation and 0.19% for extrapolation. Our approach can be used for data-efficient NN modeling for TCAD and real-time physics analysis in the spatial domain. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | A Novel Neural-Network Device Modeling Based on Physics-Informed Machine Learning | - |
dc.type | Article | - |
dc.identifier.wosid | 001085434200001 | - |
dc.identifier.scopusid | 2-s2.0-85174815136 | - |
dc.type.rims | ART | - |
dc.citation.volume | 70 | - |
dc.citation.issue | 11 | - |
dc.citation.beginningpage | 6021 | - |
dc.citation.endingpage | 6025 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON ELECTRON DEVICES | - |
dc.identifier.doi | 10.1109/TED.2023.3316635 | - |
dc.contributor.localauthor | Shin, Mincheol | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Deep operator network | - |
dc.subject.keywordAuthor | nanowire | - |
dc.subject.keywordAuthor | neural network (NN) | - |
dc.subject.keywordAuthor | physics-informed machine learning (PIML) | - |
dc.subject.keywordPlus | BOLTZMANN TRANSPORT-EQUATION | - |
dc.subject.keywordPlus | SIMULATION | - |
dc.subject.keywordPlus | FRAMEWORK | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.