Energy Efficient Superconducting Neural Networks for High-Speed Intellectual Data Processing Systems
We present the results of circuit simulations for the adiabatic flux-operating neuron. The proposed cell with one-shot calculation of activation function is based on a modified single-junction superconducting quantum interferometer. In comparison, functionally equivalent elements of the artificial n...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on applied superconductivity 2018-10, Vol.28 (7), p.1-6 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 6 |
|---|---|
| container_issue | 7 |
| container_start_page | 1 |
| container_title | IEEE transactions on applied superconductivity |
| container_volume | 28 |
| creator | Klenov, Nikolay V. Schegolev, Andrey E. Soloviev, Igor I. Bakurskiy, Sergey V. Tereshonok, Maxim V. |
| description | We present the results of circuit simulations for the adiabatic flux-operating neuron. The proposed cell with one-shot calculation of activation function is based on a modified single-junction superconducting quantum interferometer. In comparison, functionally equivalent elements of the artificial neural network (ANN) in the semiconductor-based implementations consist of approximately 20 transistors. Also in the article, we present the connecting synapse based on the adiabatic quantum flux parametron. These neurons and synapses allow constructing ANNs with a magnetic representation of information in the form of direction and/or magnitude of the magnetic flux in the superconducting circuit. We discuss the dissipation of energy during operations in the frame of the proposed concept. This value in superconducting neurons and synapses with sub-nanosecond timescale can be reduced down to 10 and 0.1 aJ, respectively. The use of the adiabatic superconducting logic circuits in our approach promises compatibility with superconducting quantum information processing systems. |
| doi_str_mv | 10.1109/TASC.2018.2836903 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TASC_2018_2836903</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8359347</ieee_id><sourcerecordid>2117130108</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-3fe359da12841132f553c128ca1350176145044476f4cc5887750ddf6d46bf233</originalsourceid><addsrcrecordid>eNo9kE1Lw0AQhhdRsFZ_gHgJeE7d2Y9kcyy12kJRIfW8xM1sTU2TuLtB-u9NqHiaGXjemeEh5BboDIBmD9t5vpgxCmrGFE8yys_IBKRUMZMgz4eeSogVY_ySXHm_pxSEEnJCymWDbneMltZWpsImRHnfoTNtU_YmVM0uesHeFfVQwk_rvnxkWxetqt1nnHeIZbRuAtY1mtAP0GMRiujNtQa9H7P50Qc8-GtyYYva481fnZL3p-V2sYo3r8_rxXwTG5bxEHOLXGZlAUwJAM6slNwMgymASwppAkJSIUSaWGGMVCpNJS1Lm5Qi-bCM8ym5P-3tXPvdow963_auGU5qBpACp0DVQMGJMq713qHVnasOhTtqoHqUqUeZepSp_2QOmbtTpkLEf14N73KR8l-3SG_M</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2117130108</pqid></control><display><type>article</type><title>Energy Efficient Superconducting Neural Networks for High-Speed Intellectual Data Processing Systems</title><source>IEEE Electronic Library (IEL)</source><creator>Klenov, Nikolay V. ; Schegolev, Andrey E. ; Soloviev, Igor I. ; Bakurskiy, Sergey V. ; Tereshonok, Maxim V.</creator><creatorcontrib>Klenov, Nikolay V. ; Schegolev, Andrey E. ; Soloviev, Igor I. ; Bakurskiy, Sergey V. ; Tereshonok, Maxim V.</creatorcontrib><description>We present the results of circuit simulations for the adiabatic flux-operating neuron. The proposed cell with one-shot calculation of activation function is based on a modified single-junction superconducting quantum interferometer. In comparison, functionally equivalent elements of the artificial neural network (ANN) in the semiconductor-based implementations consist of approximately 20 transistors. Also in the article, we present the connecting synapse based on the adiabatic quantum flux parametron. These neurons and synapses allow constructing ANNs with a magnetic representation of information in the form of direction and/or magnitude of the magnetic flux in the superconducting circuit. We discuss the dissipation of energy during operations in the frame of the proposed concept. This value in superconducting neurons and synapses with sub-nanosecond timescale can be reduced down to 10 and 0.1 aJ, respectively. The use of the adiabatic superconducting logic circuits in our approach promises compatibility with superconducting quantum information processing systems.</description><identifier>ISSN: 1051-8223</identifier><identifier>EISSN: 1558-2515</identifier><identifier>DOI: 10.1109/TASC.2018.2836903</identifier><identifier>CODEN: ITASE9</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Adiabatic flow ; Adiabatic quantum flux parametron ; artificial neural network (ANN) ; Artificial neural networks ; Computer simulation ; Data processing ; Inductance ; Josephson junctions ; Logic circuits ; Magnetic flux ; Neural networks ; Neurons ; Quantum phenomena ; Quantum theory ; Semiconductor devices ; Superconducting integrated circuits ; Superconducting logic circuits ; superconducting neuron ; superconducting quantum interferometer ; superconducting synapse ; Superconductivity ; Synapses ; Transistors</subject><ispartof>IEEE transactions on applied superconductivity, 2018-10, Vol.28 (7), p.1-6</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-3fe359da12841132f553c128ca1350176145044476f4cc5887750ddf6d46bf233</citedby><cites>FETCH-LOGICAL-c293t-3fe359da12841132f553c128ca1350176145044476f4cc5887750ddf6d46bf233</cites><orcidid>0000-0001-9735-2720</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8359347$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8359347$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Klenov, Nikolay V.</creatorcontrib><creatorcontrib>Schegolev, Andrey E.</creatorcontrib><creatorcontrib>Soloviev, Igor I.</creatorcontrib><creatorcontrib>Bakurskiy, Sergey V.</creatorcontrib><creatorcontrib>Tereshonok, Maxim V.</creatorcontrib><title>Energy Efficient Superconducting Neural Networks for High-Speed Intellectual Data Processing Systems</title><title>IEEE transactions on applied superconductivity</title><addtitle>TASC</addtitle><description>We present the results of circuit simulations for the adiabatic flux-operating neuron. The proposed cell with one-shot calculation of activation function is based on a modified single-junction superconducting quantum interferometer. In comparison, functionally equivalent elements of the artificial neural network (ANN) in the semiconductor-based implementations consist of approximately 20 transistors. Also in the article, we present the connecting synapse based on the adiabatic quantum flux parametron. These neurons and synapses allow constructing ANNs with a magnetic representation of information in the form of direction and/or magnitude of the magnetic flux in the superconducting circuit. We discuss the dissipation of energy during operations in the frame of the proposed concept. This value in superconducting neurons and synapses with sub-nanosecond timescale can be reduced down to 10 and 0.1 aJ, respectively. The use of the adiabatic superconducting logic circuits in our approach promises compatibility with superconducting quantum information processing systems.</description><subject>Adiabatic flow</subject><subject>Adiabatic quantum flux parametron</subject><subject>artificial neural network (ANN)</subject><subject>Artificial neural networks</subject><subject>Computer simulation</subject><subject>Data processing</subject><subject>Inductance</subject><subject>Josephson junctions</subject><subject>Logic circuits</subject><subject>Magnetic flux</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Quantum phenomena</subject><subject>Quantum theory</subject><subject>Semiconductor devices</subject><subject>Superconducting integrated circuits</subject><subject>Superconducting logic circuits</subject><subject>superconducting neuron</subject><subject>superconducting quantum interferometer</subject><subject>superconducting synapse</subject><subject>Superconductivity</subject><subject>Synapses</subject><subject>Transistors</subject><issn>1051-8223</issn><issn>1558-2515</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kE1Lw0AQhhdRsFZ_gHgJeE7d2Y9kcyy12kJRIfW8xM1sTU2TuLtB-u9NqHiaGXjemeEh5BboDIBmD9t5vpgxCmrGFE8yys_IBKRUMZMgz4eeSogVY_ySXHm_pxSEEnJCymWDbneMltZWpsImRHnfoTNtU_YmVM0uesHeFfVQwk_rvnxkWxetqt1nnHeIZbRuAtY1mtAP0GMRiujNtQa9H7P50Qc8-GtyYYva481fnZL3p-V2sYo3r8_rxXwTG5bxEHOLXGZlAUwJAM6slNwMgymASwppAkJSIUSaWGGMVCpNJS1Lm5Qi-bCM8ym5P-3tXPvdow963_auGU5qBpACp0DVQMGJMq713qHVnasOhTtqoHqUqUeZepSp_2QOmbtTpkLEf14N73KR8l-3SG_M</recordid><startdate>20181001</startdate><enddate>20181001</enddate><creator>Klenov, Nikolay V.</creator><creator>Schegolev, Andrey E.</creator><creator>Soloviev, Igor I.</creator><creator>Bakurskiy, Sergey V.</creator><creator>Tereshonok, Maxim V.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0001-9735-2720</orcidid></search><sort><creationdate>20181001</creationdate><title>Energy Efficient Superconducting Neural Networks for High-Speed Intellectual Data Processing Systems</title><author>Klenov, Nikolay V. ; Schegolev, Andrey E. ; Soloviev, Igor I. ; Bakurskiy, Sergey V. ; Tereshonok, Maxim V.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-3fe359da12841132f553c128ca1350176145044476f4cc5887750ddf6d46bf233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Adiabatic flow</topic><topic>Adiabatic quantum flux parametron</topic><topic>artificial neural network (ANN)</topic><topic>Artificial neural networks</topic><topic>Computer simulation</topic><topic>Data processing</topic><topic>Inductance</topic><topic>Josephson junctions</topic><topic>Logic circuits</topic><topic>Magnetic flux</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Quantum phenomena</topic><topic>Quantum theory</topic><topic>Semiconductor devices</topic><topic>Superconducting integrated circuits</topic><topic>Superconducting logic circuits</topic><topic>superconducting neuron</topic><topic>superconducting quantum interferometer</topic><topic>superconducting synapse</topic><topic>Superconductivity</topic><topic>Synapses</topic><topic>Transistors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Klenov, Nikolay V.</creatorcontrib><creatorcontrib>Schegolev, Andrey E.</creatorcontrib><creatorcontrib>Soloviev, Igor I.</creatorcontrib><creatorcontrib>Bakurskiy, Sergey V.</creatorcontrib><creatorcontrib>Tereshonok, Maxim V.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on applied superconductivity</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Klenov, Nikolay V.</au><au>Schegolev, Andrey E.</au><au>Soloviev, Igor I.</au><au>Bakurskiy, Sergey V.</au><au>Tereshonok, Maxim V.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Energy Efficient Superconducting Neural Networks for High-Speed Intellectual Data Processing Systems</atitle><jtitle>IEEE transactions on applied superconductivity</jtitle><stitle>TASC</stitle><date>2018-10-01</date><risdate>2018</risdate><volume>28</volume><issue>7</issue><spage>1</spage><epage>6</epage><pages>1-6</pages><issn>1051-8223</issn><eissn>1558-2515</eissn><coden>ITASE9</coden><abstract>We present the results of circuit simulations for the adiabatic flux-operating neuron. The proposed cell with one-shot calculation of activation function is based on a modified single-junction superconducting quantum interferometer. In comparison, functionally equivalent elements of the artificial neural network (ANN) in the semiconductor-based implementations consist of approximately 20 transistors. Also in the article, we present the connecting synapse based on the adiabatic quantum flux parametron. These neurons and synapses allow constructing ANNs with a magnetic representation of information in the form of direction and/or magnitude of the magnetic flux in the superconducting circuit. We discuss the dissipation of energy during operations in the frame of the proposed concept. This value in superconducting neurons and synapses with sub-nanosecond timescale can be reduced down to 10 and 0.1 aJ, respectively. The use of the adiabatic superconducting logic circuits in our approach promises compatibility with superconducting quantum information processing systems.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TASC.2018.2836903</doi><tpages>6</tpages><orcidid>https://orcid.org/0000-0001-9735-2720</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1051-8223 |
| ispartof | IEEE transactions on applied superconductivity, 2018-10, Vol.28 (7), p.1-6 |
| issn | 1051-8223 1558-2515 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_TASC_2018_2836903 |
| source | IEEE Electronic Library (IEL) |
| subjects | Adiabatic flow Adiabatic quantum flux parametron artificial neural network (ANN) Artificial neural networks Computer simulation Data processing Inductance Josephson junctions Logic circuits Magnetic flux Neural networks Neurons Quantum phenomena Quantum theory Semiconductor devices Superconducting integrated circuits Superconducting logic circuits superconducting neuron superconducting quantum interferometer superconducting synapse Superconductivity Synapses Transistors |
| title | Energy Efficient Superconducting Neural Networks for High-Speed Intellectual Data Processing Systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T05%3A29%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Energy%20Efficient%20Superconducting%20Neural%20Networks%20for%20High-Speed%20Intellectual%20Data%20Processing%20Systems&rft.jtitle=IEEE%20transactions%20on%20applied%20superconductivity&rft.au=Klenov,%20Nikolay%20V.&rft.date=2018-10-01&rft.volume=28&rft.issue=7&rft.spage=1&rft.epage=6&rft.pages=1-6&rft.issn=1051-8223&rft.eissn=1558-2515&rft.coden=ITASE9&rft_id=info:doi/10.1109/TASC.2018.2836903&rft_dat=%3Cproquest_RIE%3E2117130108%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2117130108&rft_id=info:pmid/&rft_ieee_id=8359347&rfr_iscdi=true |