A large-signal characterization of an HEMT using a multilayered neural network

We propose an approach to describe the large-signal behavior of a high electron-mobility transistor (HEMT) by using a multilayered neural network. To conveniently implement this in standard circuit simulators, we extracted the HEMT's bias dependent behavior in terms of conventional small-signal...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on microwave theory and techniques 1997-09, Vol.45 (9), p.1630-1633
Main Authors: Shirakawa, K., Shimiz, M., Okubo, N., Daido, Y.
Format: Article
Language:English
Subjects:
Analytical models
Circuit simulation
Equations
Extrapolation
HEMTs
MODFETs
Multi-layer neural network
Neural networks
Neurons
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c339t-511a1c4803e30d9f24d3b8117d101e2945bb0524204623f823cc6448251e3e5d3
cites cdi_FETCH-LOGICAL-c339t-511a1c4803e30d9f24d3b8117d101e2945bb0524204623f823cc6448251e3e5d3
container_end_page 1633
container_issue 9
container_start_page 1630
container_title IEEE transactions on microwave theory and techniques
container_volume 45
creator Shirakawa, K.
Shimiz, M.
Okubo, N.
Daido, Y.
description We propose an approach to describe the large-signal behavior of a high electron-mobility transistor (HEMT) by using a multilayered neural network. To conveniently implement this in standard circuit simulators, we extracted the HEMT's bias dependent behavior in terms of conventional small-signal equivalent-circuit elements. We successfully represented seven intrinsic elements with a five-layered neural network (composed of 28 neurons) whose inputs are the gate-to source bias (V/sub gs/,) and drain-to-source bias (V/sub ds/) A "well-trained" neural network shows excellent accuracy and generates good extrapolations.
doi_str_mv 10.1109/22.622932
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_miscellaneous_28361065</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>622932</ieee_id><sourcerecordid>28912863</sourcerecordid><originalsourceid>FETCH-LOGICAL-c339t-511a1c4803e30d9f24d3b8117d101e2945bb0524204623f823cc6448251e3e5d3</originalsourceid><addsrcrecordid>eNqN0U1Lw0AQBuBFFKzVg1dPexI8pO7MfjR7LKVaoeqlnsN2M6nRNKm7CVJ_vZEWr3oahnlmGHgZuwQxAhD2FnFkEK3EIzYArceJNWNxzAZCQJpYlYpTdhbjW98qLdIBe5rwyoU1JbFc167i_tUF51sK5Zdry6bmTcFdzeezxyXvYlmvueObrmrLyu0oUM5r6kK_V1P72YT3c3ZSuCrSxaEO2cvdbDmdJ4vn-4fpZJF4KW2baAAHvv9GkhS5LVDlcpUCjHMQQGiVXq2ERoVCGZRFitJ7o1SKGkiSzuWQXe_vbkPz0VFss00ZPVWVq6npYoapBUyN_AeUBoTRf0OjDViBPbzZQx-aGAMV2TaUGxd2GYjsJ4MMMdtn0NurvS2J6Ncdht8kCH7X</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>26561902</pqid></control><display><type>article</type><title>A large-signal characterization of an HEMT using a multilayered neural network</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Shirakawa, K. ; Shimiz, M. ; Okubo, N. ; Daido, Y.</creator><creatorcontrib>Shirakawa, K. ; Shimiz, M. ; Okubo, N. ; Daido, Y.</creatorcontrib><description>We propose an approach to describe the large-signal behavior of a high electron-mobility transistor (HEMT) by using a multilayered neural network. To conveniently implement this in standard circuit simulators, we extracted the HEMT's bias dependent behavior in terms of conventional small-signal equivalent-circuit elements. We successfully represented seven intrinsic elements with a five-layered neural network (composed of 28 neurons) whose inputs are the gate-to source bias (V/sub gs/,) and drain-to-source bias (V/sub ds/) A "well-trained" neural network shows excellent accuracy and generates good extrapolations.</description><identifier>ISSN: 0018-9480</identifier><identifier>EISSN: 1557-9670</identifier><identifier>DOI: 10.1109/22.622932</identifier><identifier>CODEN: IETMAB</identifier><language>eng</language><publisher>IEEE</publisher><subject>Analytical models ; Circuit simulation ; Equations ; Extrapolation ; HEMTs ; MODFETs ; Multi-layer neural network ; Neural networks ; Neurons</subject><ispartof>IEEE transactions on microwave theory and techniques, 1997-09, Vol.45 (9), p.1630-1633</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c339t-511a1c4803e30d9f24d3b8117d101e2945bb0524204623f823cc6448251e3e5d3</citedby><cites>FETCH-LOGICAL-c339t-511a1c4803e30d9f24d3b8117d101e2945bb0524204623f823cc6448251e3e5d3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/622932$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Shirakawa, K.</creatorcontrib><creatorcontrib>Shimiz, M.</creatorcontrib><creatorcontrib>Okubo, N.</creatorcontrib><creatorcontrib>Daido, Y.</creatorcontrib><title>A large-signal characterization of an HEMT using a multilayered neural network</title><title>IEEE transactions on microwave theory and techniques</title><addtitle>TMTT</addtitle><description>We propose an approach to describe the large-signal behavior of a high electron-mobility transistor (HEMT) by using a multilayered neural network. To conveniently implement this in standard circuit simulators, we extracted the HEMT's bias dependent behavior in terms of conventional small-signal equivalent-circuit elements. We successfully represented seven intrinsic elements with a five-layered neural network (composed of 28 neurons) whose inputs are the gate-to source bias (V/sub gs/,) and drain-to-source bias (V/sub ds/) A "well-trained" neural network shows excellent accuracy and generates good extrapolations.</description><subject>Analytical models</subject><subject>Circuit simulation</subject><subject>Equations</subject><subject>Extrapolation</subject><subject>HEMTs</subject><subject>MODFETs</subject><subject>Multi-layer neural network</subject><subject>Neural networks</subject><subject>Neurons</subject><issn>0018-9480</issn><issn>1557-9670</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1997</creationdate><recordtype>article</recordtype><recordid>eNqN0U1Lw0AQBuBFFKzVg1dPexI8pO7MfjR7LKVaoeqlnsN2M6nRNKm7CVJ_vZEWr3oahnlmGHgZuwQxAhD2FnFkEK3EIzYArceJNWNxzAZCQJpYlYpTdhbjW98qLdIBe5rwyoU1JbFc167i_tUF51sK5Zdry6bmTcFdzeezxyXvYlmvueObrmrLyu0oUM5r6kK_V1P72YT3c3ZSuCrSxaEO2cvdbDmdJ4vn-4fpZJF4KW2baAAHvv9GkhS5LVDlcpUCjHMQQGiVXq2ERoVCGZRFitJ7o1SKGkiSzuWQXe_vbkPz0VFss00ZPVWVq6npYoapBUyN_AeUBoTRf0OjDViBPbzZQx-aGAMV2TaUGxd2GYjsJ4MMMdtn0NurvS2J6Ncdht8kCH7X</recordid><startdate>19970901</startdate><enddate>19970901</enddate><creator>Shirakawa, K.</creator><creator>Shimiz, M.</creator><creator>Okubo, N.</creator><creator>Daido, Y.</creator><general>IEEE</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>7SP</scope><scope>7U5</scope></search><sort><creationdate>19970901</creationdate><title>A large-signal characterization of an HEMT using a multilayered neural network</title><author>Shirakawa, K. ; Shimiz, M. ; Okubo, N. ; Daido, Y.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c339t-511a1c4803e30d9f24d3b8117d101e2945bb0524204623f823cc6448251e3e5d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1997</creationdate><topic>Analytical models</topic><topic>Circuit simulation</topic><topic>Equations</topic><topic>Extrapolation</topic><topic>HEMTs</topic><topic>MODFETs</topic><topic>Multi-layer neural network</topic><topic>Neural networks</topic><topic>Neurons</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shirakawa, K.</creatorcontrib><creatorcontrib>Shimiz, M.</creatorcontrib><creatorcontrib>Okubo, N.</creatorcontrib><creatorcontrib>Daido, Y.</creatorcontrib><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><jtitle>IEEE transactions on microwave theory and techniques</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shirakawa, K.</au><au>Shimiz, M.</au><au>Okubo, N.</au><au>Daido, Y.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A large-signal characterization of an HEMT using a multilayered neural network</atitle><jtitle>IEEE transactions on microwave theory and techniques</jtitle><stitle>TMTT</stitle><date>1997-09-01</date><risdate>1997</risdate><volume>45</volume><issue>9</issue><spage>1630</spage><epage>1633</epage><pages>1630-1633</pages><issn>0018-9480</issn><eissn>1557-9670</eissn><coden>IETMAB</coden><abstract>We propose an approach to describe the large-signal behavior of a high electron-mobility transistor (HEMT) by using a multilayered neural network. To conveniently implement this in standard circuit simulators, we extracted the HEMT's bias dependent behavior in terms of conventional small-signal equivalent-circuit elements. We successfully represented seven intrinsic elements with a five-layered neural network (composed of 28 neurons) whose inputs are the gate-to source bias (V/sub gs/,) and drain-to-source bias (V/sub ds/) A "well-trained" neural network shows excellent accuracy and generates good extrapolations.</abstract><pub>IEEE</pub><doi>10.1109/22.622932</doi><tpages>4</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0018-9480
ispartof IEEE transactions on microwave theory and techniques, 1997-09, Vol.45 (9), p.1630-1633
issn 0018-9480
1557-9670
language eng
recordid cdi_proquest_miscellaneous_28361065
source IEEE Electronic Library (IEL) Journals
subjects Analytical models
Circuit simulation
Equations
Extrapolation
HEMTs
MODFETs
Multi-layer neural network
Neural networks
Neurons
title A large-signal characterization of an HEMT using a multilayered neural network
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T20%3A18%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20large-signal%20characterization%20of%20an%20HEMT%20using%20a%20multilayered%20neural%20network&rft.jtitle=IEEE%20transactions%20on%20microwave%20theory%20and%20techniques&rft.au=Shirakawa,%20K.&rft.date=1997-09-01&rft.volume=45&rft.issue=9&rft.spage=1630&rft.epage=1633&rft.pages=1630-1633&rft.issn=0018-9480&rft.eissn=1557-9670&rft.coden=IETMAB&rft_id=info:doi/10.1109/22.622932&rft_dat=%3Cproquest_ieee_%3E28912863%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c339t-511a1c4803e30d9f24d3b8117d101e2945bb0524204623f823cc6448251e3e5d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=26561902&rft_id=info:pmid/&rft_ieee_id=622932&rfr_iscdi=true