Multinary Data Processing Based on Nonlinear Synaptic Devices
Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is neces...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Kim, Myungjun [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Minerals, Metals & Materials Society 2021 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Journal of electronic materials - Springer US, 1972, 50(2021), 6 vom: 25. März, Seite 3471-3477 |
|---|---|
| Übergeordnetes Werk: |
volume:50 ; year:2021 ; number:6 ; day:25 ; month:03 ; pages:3471-3477 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11664-021-08841-8 |
|---|
| Katalog-ID: |
OLC212557487X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC212557487X | ||
| 003 | DE-627 | ||
| 005 | 20230505103651.0 | ||
| 007 | tu | ||
| 008 | 230505s2021 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11664-021-08841-8 |2 doi | |
| 035 | |a (DE-627)OLC212557487X | ||
| 035 | |a (DE-He213)s11664-021-08841-8-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 670 |q VZ |
| 100 | 1 | |a Kim, Myungjun |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Multinary Data Processing Based on Nonlinear Synaptic Devices |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Minerals, Metals & Materials Society 2021 | ||
| 520 | |a Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. | ||
| 650 | 4 | |a Neuromorphic system | |
| 650 | 4 | |a analog neuron | |
| 650 | 4 | |a synapse device | |
| 650 | 4 | |a multinary data | |
| 650 | 4 | |a nonlinear synaptic device | |
| 700 | 1 | |a Lee, Jae-Eun |4 aut | |
| 700 | 1 | |a Lee, Chuljun |4 aut | |
| 700 | 1 | |a Song, Yubin |4 aut | |
| 700 | 1 | |a Han, Geonhui |4 aut | |
| 700 | 1 | |a Seo, Jongseon |4 aut | |
| 700 | 1 | |a Kim, Dong-Wook |4 aut | |
| 700 | 1 | |a Seo, Young-Ho |4 aut | |
| 700 | 1 | |a Hwang, Hyunsang |4 aut | |
| 700 | 1 | |a Lee, Daeseok |0 (orcid)0000-0002-4548-2387 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of electronic materials |d Springer US, 1972 |g 50(2021), 6 vom: 25. März, Seite 3471-3477 |w (DE-627)129398233 |w (DE-600)186069-0 |w (DE-576)014781387 |x 0361-5235 |7 nnns |
| 773 | 1 | 8 | |g volume:50 |g year:2021 |g number:6 |g day:25 |g month:03 |g pages:3471-3477 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s11664-021-08841-8 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-TEC | ||
| 912 | |a SSG-OLC-PHY | ||
| 951 | |a AR | ||
| 952 | |d 50 |j 2021 |e 6 |b 25 |c 03 |h 3471-3477 | ||
| author_variant |
m k mk j e l jel c l cl y s ys g h gh j s js d w k dwk y h s yhs h h hh d l dl |
|---|---|
| matchkey_str |
article:03615235:2021----::utnrdtpoesnbsdnolna |
| hierarchy_sort_str |
2021 |
| publishDate |
2021 |
| allfields |
10.1007/s11664-021-08841-8 doi (DE-627)OLC212557487X (DE-He213)s11664-021-08841-8-p DE-627 ger DE-627 rakwb eng 670 VZ Kim, Myungjun verfasserin aut Multinary Data Processing Based on Nonlinear Synaptic Devices 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Minerals, Metals & Materials Society 2021 Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. Neuromorphic system analog neuron synapse device multinary data nonlinear synaptic device Lee, Jae-Eun aut Lee, Chuljun aut Song, Yubin aut Han, Geonhui aut Seo, Jongseon aut Kim, Dong-Wook aut Seo, Young-Ho aut Hwang, Hyunsang aut Lee, Daeseok (orcid)0000-0002-4548-2387 aut Enthalten in Journal of electronic materials Springer US, 1972 50(2021), 6 vom: 25. März, Seite 3471-3477 (DE-627)129398233 (DE-600)186069-0 (DE-576)014781387 0361-5235 nnns volume:50 year:2021 number:6 day:25 month:03 pages:3471-3477 https://doi.org/10.1007/s11664-021-08841-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-PHY AR 50 2021 6 25 03 3471-3477 |
| spelling |
10.1007/s11664-021-08841-8 doi (DE-627)OLC212557487X (DE-He213)s11664-021-08841-8-p DE-627 ger DE-627 rakwb eng 670 VZ Kim, Myungjun verfasserin aut Multinary Data Processing Based on Nonlinear Synaptic Devices 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Minerals, Metals & Materials Society 2021 Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. Neuromorphic system analog neuron synapse device multinary data nonlinear synaptic device Lee, Jae-Eun aut Lee, Chuljun aut Song, Yubin aut Han, Geonhui aut Seo, Jongseon aut Kim, Dong-Wook aut Seo, Young-Ho aut Hwang, Hyunsang aut Lee, Daeseok (orcid)0000-0002-4548-2387 aut Enthalten in Journal of electronic materials Springer US, 1972 50(2021), 6 vom: 25. März, Seite 3471-3477 (DE-627)129398233 (DE-600)186069-0 (DE-576)014781387 0361-5235 nnns volume:50 year:2021 number:6 day:25 month:03 pages:3471-3477 https://doi.org/10.1007/s11664-021-08841-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-PHY AR 50 2021 6 25 03 3471-3477 |
| allfields_unstemmed |
10.1007/s11664-021-08841-8 doi (DE-627)OLC212557487X (DE-He213)s11664-021-08841-8-p DE-627 ger DE-627 rakwb eng 670 VZ Kim, Myungjun verfasserin aut Multinary Data Processing Based on Nonlinear Synaptic Devices 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Minerals, Metals & Materials Society 2021 Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. Neuromorphic system analog neuron synapse device multinary data nonlinear synaptic device Lee, Jae-Eun aut Lee, Chuljun aut Song, Yubin aut Han, Geonhui aut Seo, Jongseon aut Kim, Dong-Wook aut Seo, Young-Ho aut Hwang, Hyunsang aut Lee, Daeseok (orcid)0000-0002-4548-2387 aut Enthalten in Journal of electronic materials Springer US, 1972 50(2021), 6 vom: 25. März, Seite 3471-3477 (DE-627)129398233 (DE-600)186069-0 (DE-576)014781387 0361-5235 nnns volume:50 year:2021 number:6 day:25 month:03 pages:3471-3477 https://doi.org/10.1007/s11664-021-08841-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-PHY AR 50 2021 6 25 03 3471-3477 |
| allfieldsGer |
10.1007/s11664-021-08841-8 doi (DE-627)OLC212557487X (DE-He213)s11664-021-08841-8-p DE-627 ger DE-627 rakwb eng 670 VZ Kim, Myungjun verfasserin aut Multinary Data Processing Based on Nonlinear Synaptic Devices 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Minerals, Metals & Materials Society 2021 Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. Neuromorphic system analog neuron synapse device multinary data nonlinear synaptic device Lee, Jae-Eun aut Lee, Chuljun aut Song, Yubin aut Han, Geonhui aut Seo, Jongseon aut Kim, Dong-Wook aut Seo, Young-Ho aut Hwang, Hyunsang aut Lee, Daeseok (orcid)0000-0002-4548-2387 aut Enthalten in Journal of electronic materials Springer US, 1972 50(2021), 6 vom: 25. März, Seite 3471-3477 (DE-627)129398233 (DE-600)186069-0 (DE-576)014781387 0361-5235 nnns volume:50 year:2021 number:6 day:25 month:03 pages:3471-3477 https://doi.org/10.1007/s11664-021-08841-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-PHY AR 50 2021 6 25 03 3471-3477 |
| allfieldsSound |
10.1007/s11664-021-08841-8 doi (DE-627)OLC212557487X (DE-He213)s11664-021-08841-8-p DE-627 ger DE-627 rakwb eng 670 VZ Kim, Myungjun verfasserin aut Multinary Data Processing Based on Nonlinear Synaptic Devices 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Minerals, Metals & Materials Society 2021 Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. Neuromorphic system analog neuron synapse device multinary data nonlinear synaptic device Lee, Jae-Eun aut Lee, Chuljun aut Song, Yubin aut Han, Geonhui aut Seo, Jongseon aut Kim, Dong-Wook aut Seo, Young-Ho aut Hwang, Hyunsang aut Lee, Daeseok (orcid)0000-0002-4548-2387 aut Enthalten in Journal of electronic materials Springer US, 1972 50(2021), 6 vom: 25. März, Seite 3471-3477 (DE-627)129398233 (DE-600)186069-0 (DE-576)014781387 0361-5235 nnns volume:50 year:2021 number:6 day:25 month:03 pages:3471-3477 https://doi.org/10.1007/s11664-021-08841-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-PHY AR 50 2021 6 25 03 3471-3477 |
| language |
English |
| source |
Enthalten in Journal of electronic materials 50(2021), 6 vom: 25. März, Seite 3471-3477 volume:50 year:2021 number:6 day:25 month:03 pages:3471-3477 |
| sourceStr |
Enthalten in Journal of electronic materials 50(2021), 6 vom: 25. März, Seite 3471-3477 volume:50 year:2021 number:6 day:25 month:03 pages:3471-3477 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Neuromorphic system analog neuron synapse device multinary data nonlinear synaptic device |
| dewey-raw |
670 |
| isfreeaccess_bool |
false |
| container_title |
Journal of electronic materials |
| authorswithroles_txt_mv |
Kim, Myungjun @@aut@@ Lee, Jae-Eun @@aut@@ Lee, Chuljun @@aut@@ Song, Yubin @@aut@@ Han, Geonhui @@aut@@ Seo, Jongseon @@aut@@ Kim, Dong-Wook @@aut@@ Seo, Young-Ho @@aut@@ Hwang, Hyunsang @@aut@@ Lee, Daeseok @@aut@@ |
| publishDateDaySort_date |
2021-03-25T00:00:00Z |
| hierarchy_top_id |
129398233 |
| dewey-sort |
3670 |
| id |
OLC212557487X |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC212557487X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505103651.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230505s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11664-021-08841-8</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC212557487X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11664-021-08841-8-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">670</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Kim, Myungjun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multinary Data Processing Based on Nonlinear Synaptic Devices</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Minerals, Metals & Materials Society 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Neuromorphic system</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">analog neuron</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">synapse device</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">multinary data</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">nonlinear synaptic device</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Jae-Eun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Chuljun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Song, Yubin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, Geonhui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Jongseon</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kim, Dong-Wook</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Young-Ho</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hwang, Hyunsang</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Daeseok</subfield><subfield code="0">(orcid)0000-0002-4548-2387</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Journal of electronic materials</subfield><subfield code="d">Springer US, 1972</subfield><subfield code="g">50(2021), 6 vom: 25. März, Seite 3471-3477</subfield><subfield code="w">(DE-627)129398233</subfield><subfield code="w">(DE-600)186069-0</subfield><subfield code="w">(DE-576)014781387</subfield><subfield code="x">0361-5235</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:50</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:6</subfield><subfield code="g">day:25</subfield><subfield code="g">month:03</subfield><subfield code="g">pages:3471-3477</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11664-021-08841-8</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHY</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">50</subfield><subfield code="j">2021</subfield><subfield code="e">6</subfield><subfield code="b">25</subfield><subfield code="c">03</subfield><subfield code="h">3471-3477</subfield></datafield></record></collection>
|
| author |
Kim, Myungjun |
| spellingShingle |
Kim, Myungjun ddc 670 misc Neuromorphic system misc analog neuron misc synapse device misc multinary data misc nonlinear synaptic device Multinary Data Processing Based on Nonlinear Synaptic Devices |
| authorStr |
Kim, Myungjun |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)129398233 |
| format |
Article |
| dewey-ones |
670 - Manufacturing |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut aut aut aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0361-5235 |
| topic_title |
670 VZ Multinary Data Processing Based on Nonlinear Synaptic Devices Neuromorphic system analog neuron synapse device multinary data nonlinear synaptic device |
| topic |
ddc 670 misc Neuromorphic system misc analog neuron misc synapse device misc multinary data misc nonlinear synaptic device |
| topic_unstemmed |
ddc 670 misc Neuromorphic system misc analog neuron misc synapse device misc multinary data misc nonlinear synaptic device |
| topic_browse |
ddc 670 misc Neuromorphic system misc analog neuron misc synapse device misc multinary data misc nonlinear synaptic device |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Journal of electronic materials |
| hierarchy_parent_id |
129398233 |
| dewey-tens |
670 - Manufacturing |
| hierarchy_top_title |
Journal of electronic materials |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)129398233 (DE-600)186069-0 (DE-576)014781387 |
| title |
Multinary Data Processing Based on Nonlinear Synaptic Devices |
| ctrlnum |
(DE-627)OLC212557487X (DE-He213)s11664-021-08841-8-p |
| title_full |
Multinary Data Processing Based on Nonlinear Synaptic Devices |
| author_sort |
Kim, Myungjun |
| journal |
Journal of electronic materials |
| journalStr |
Journal of electronic materials |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
txt |
| container_start_page |
3471 |
| author_browse |
Kim, Myungjun Lee, Jae-Eun Lee, Chuljun Song, Yubin Han, Geonhui Seo, Jongseon Kim, Dong-Wook Seo, Young-Ho Hwang, Hyunsang Lee, Daeseok |
| container_volume |
50 |
| class |
670 VZ |
| format_se |
Aufsätze |
| author-letter |
Kim, Myungjun |
| doi_str_mv |
10.1007/s11664-021-08841-8 |
| normlink |
(ORCID)0000-0002-4548-2387 |
| normlink_prefix_str_mv |
(orcid)0000-0002-4548-2387 |
| dewey-full |
670 |
| title_sort |
multinary data processing based on nonlinear synaptic devices |
| title_auth |
Multinary Data Processing Based on Nonlinear Synaptic Devices |
| abstract |
Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. © The Minerals, Metals & Materials Society 2021 |
| abstractGer |
Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. © The Minerals, Metals & Materials Society 2021 |
| abstract_unstemmed |
Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%. © The Minerals, Metals & Materials Society 2021 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-PHY |
| container_issue |
6 |
| title_short |
Multinary Data Processing Based on Nonlinear Synaptic Devices |
| url |
https://doi.org/10.1007/s11664-021-08841-8 |
| remote_bool |
false |
| author2 |
Lee, Jae-Eun Lee, Chuljun Song, Yubin Han, Geonhui Seo, Jongseon Kim, Dong-Wook Seo, Young-Ho Hwang, Hyunsang Lee, Daeseok |
| author2Str |
Lee, Jae-Eun Lee, Chuljun Song, Yubin Han, Geonhui Seo, Jongseon Kim, Dong-Wook Seo, Young-Ho Hwang, Hyunsang Lee, Daeseok |
| ppnlink |
129398233 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11664-021-08841-8 |
| up_date |
2024-07-04T04:09:53.719Z |
| _version_ |
1803620129145094144 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC212557487X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505103651.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230505s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11664-021-08841-8</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC212557487X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11664-021-08841-8-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">670</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Kim, Myungjun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multinary Data Processing Based on Nonlinear Synaptic Devices</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Minerals, Metals & Materials Society 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Stasis weight ($$\hbox {G}_s$$) that is an independent weight on applied input pulse amplitude was demonstrated for multinary data processing in a synaptic device-based neuromorphic system. Because multinary data is implemented as various input pulse amplitudes, the $$\hbox {G}_s$$ is necessary for high inference accuracy. Typically, synaptic devices exhibit nonlinear current–voltage characteristics (nonlinear device) and have different weight values depending on the applied input pulse amplitudes ($$\hbox {G}_{{\mathrm{ns}}}$$). Therefore, to achieve high inference accuracy, we proposed pulse modulation circuits that can transform the pulse amplitude into pulse width or number. As a result, the $$\hbox {G}_s$$ was obtained from the nonlinear device possessing the $$\hbox {G}_{{\mathrm{ns}}}$$, and the inference accuracy of the simulated MNIST data set was obviously improved from 29.34% to 97.6%.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Neuromorphic system</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">analog neuron</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">synapse device</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">multinary data</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">nonlinear synaptic device</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Jae-Eun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Chuljun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Song, Yubin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, Geonhui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Jongseon</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kim, Dong-Wook</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Young-Ho</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hwang, Hyunsang</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Daeseok</subfield><subfield code="0">(orcid)0000-0002-4548-2387</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Journal of electronic materials</subfield><subfield code="d">Springer US, 1972</subfield><subfield code="g">50(2021), 6 vom: 25. März, Seite 3471-3477</subfield><subfield code="w">(DE-627)129398233</subfield><subfield code="w">(DE-600)186069-0</subfield><subfield code="w">(DE-576)014781387</subfield><subfield code="x">0361-5235</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:50</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:6</subfield><subfield code="g">day:25</subfield><subfield code="g">month:03</subfield><subfield code="g">pages:3471-3477</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11664-021-08841-8</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHY</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">50</subfield><subfield code="j">2021</subfield><subfield code="e">6</subfield><subfield code="b">25</subfield><subfield code="c">03</subfield><subfield code="h">3471-3477</subfield></datafield></record></collection>
|
| score |
7.401019 |