Quantum neuron with real weights

Quantum neuron with real weights

This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical–quantum approach, considering the delta rule to update the values of the weights in a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural networks 2021-11, Vol.143, p.698-708
Hauptverfasser: Monteiro, Cláudio A., Filho, Gustavo I.S., Costa, Matheus Hopper J., de Paula Neto, Fernando M., de Oliveira, Wilson R.
Format: Artikel
Sprache:eng
Schlagworte:
Artificial intelligence
Machine learning
Quantum artificial neurons
Quantum computing
Quantum machine learning
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 708
container_issue
container_start_page 698
container_title Neural networks
container_volume 143
creator Monteiro, Cláudio A.
Filho, Gustavo I.S.
Costa, Matheus Hopper J.
de Paula Neto, Fernando M.
de Oliveira, Wilson R.
description This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical–quantum approach, considering the delta rule to update the values of the weights in an image database of three distinct patterns. We performed classical simulations and also executed experiments in an actual small-scale quantum processor. The results of the experiments show that the proposed quantum real neuron model has a good generalisation capacity, demonstrating better accuracy than the traditional binary quantum perceptron model.
doi_str_mv 10.1016/j.neunet.2021.07.034
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2563427954</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0893608021003051</els_id><sourcerecordid>2563427954</sourcerecordid><originalsourceid>FETCH-LOGICAL-c339t-12264836852d310f6dfb126861c79c2538ac7ad025053a0eac3bd5f64148ad523</originalsourceid><addsrcrecordid>eNp9kM1KxDAYRYMoOI6-gYsu3bR--W26EWTwDwZE0HXIpF-dlE47JqmDb2-HunZ1N_ceuIeQawoFBapu26LHscdUMGC0gLIALk7Iguqyylmp2SlZgK54rkDDObmIsQUApQVfkOxttH0ad9lECEOfHXzaZgFtlx3Qf25TvCRnje0iXv3lknw8PryvnvP169PL6n6dO86rlFPGlNBcaclqTqFRdbOhTGlFXVk5Jrm2rrQ1MAmSW0Dr-KaWjRJUaFtLxpfkZubuw_A1Ykxm56PDrrM9DmM0TCouWFlJMVXFXHVhiDFgY_bB72z4MRTMUYhpzSzEHIUYKM0kZJrdzTOcbnx7DCY6j73D2gd0ydSD_x_wCxbCaVI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2563427954</pqid></control><display><type>article</type><title>Quantum neuron with real weights</title><source>ScienceDirect Journals (5 years ago - present)</source><creator>Monteiro, Cláudio A. ; Filho, Gustavo I.S. ; Costa, Matheus Hopper J. ; de Paula Neto, Fernando M. ; de Oliveira, Wilson R.</creator><creatorcontrib>Monteiro, Cláudio A. ; Filho, Gustavo I.S. ; Costa, Matheus Hopper J. ; de Paula Neto, Fernando M. ; de Oliveira, Wilson R.</creatorcontrib><description>This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical–quantum approach, considering the delta rule to update the values of the weights in an image database of three distinct patterns. We performed classical simulations and also executed experiments in an actual small-scale quantum processor. The results of the experiments show that the proposed quantum real neuron model has a good generalisation capacity, demonstrating better accuracy than the traditional binary quantum perceptron model.</description><identifier>ISSN: 0893-6080</identifier><identifier>EISSN: 1879-2782</identifier><identifier>DOI: 10.1016/j.neunet.2021.07.034</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Artificial intelligence ; Machine learning ; Quantum artificial neurons ; Quantum computing ; Quantum machine learning</subject><ispartof>Neural networks, 2021-11, Vol.143, p.698-708</ispartof><rights>2021 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c339t-12264836852d310f6dfb126861c79c2538ac7ad025053a0eac3bd5f64148ad523</citedby><cites>FETCH-LOGICAL-c339t-12264836852d310f6dfb126861c79c2538ac7ad025053a0eac3bd5f64148ad523</cites><orcidid>0000-0002-7986-2695 ; 0000-0002-3261-8265 ; 0000-0003-4264-1124</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.neunet.2021.07.034$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3548,27923,27924,45994</link.rule.ids></links><search><creatorcontrib>Monteiro, Cláudio A.</creatorcontrib><creatorcontrib>Filho, Gustavo I.S.</creatorcontrib><creatorcontrib>Costa, Matheus Hopper J.</creatorcontrib><creatorcontrib>de Paula Neto, Fernando M.</creatorcontrib><creatorcontrib>de Oliveira, Wilson R.</creatorcontrib><title>Quantum neuron with real weights</title><title>Neural networks</title><description>This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical–quantum approach, considering the delta rule to update the values of the weights in an image database of three distinct patterns. We performed classical simulations and also executed experiments in an actual small-scale quantum processor. The results of the experiments show that the proposed quantum real neuron model has a good generalisation capacity, demonstrating better accuracy than the traditional binary quantum perceptron model.</description><subject>Artificial intelligence</subject><subject>Machine learning</subject><subject>Quantum artificial neurons</subject><subject>Quantum computing</subject><subject>Quantum machine learning</subject><issn>0893-6080</issn><issn>1879-2782</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kM1KxDAYRYMoOI6-gYsu3bR--W26EWTwDwZE0HXIpF-dlE47JqmDb2-HunZ1N_ceuIeQawoFBapu26LHscdUMGC0gLIALk7Iguqyylmp2SlZgK54rkDDObmIsQUApQVfkOxttH0ad9lECEOfHXzaZgFtlx3Qf25TvCRnje0iXv3lknw8PryvnvP169PL6n6dO86rlFPGlNBcaclqTqFRdbOhTGlFXVk5Jrm2rrQ1MAmSW0Dr-KaWjRJUaFtLxpfkZubuw_A1Ykxm56PDrrM9DmM0TCouWFlJMVXFXHVhiDFgY_bB72z4MRTMUYhpzSzEHIUYKM0kZJrdzTOcbnx7DCY6j73D2gd0ydSD_x_wCxbCaVI</recordid><startdate>202111</startdate><enddate>202111</enddate><creator>Monteiro, Cláudio A.</creator><creator>Filho, Gustavo I.S.</creator><creator>Costa, Matheus Hopper J.</creator><creator>de Paula Neto, Fernando M.</creator><creator>de Oliveira, Wilson R.</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-7986-2695</orcidid><orcidid>https://orcid.org/0000-0002-3261-8265</orcidid><orcidid>https://orcid.org/0000-0003-4264-1124</orcidid></search><sort><creationdate>202111</creationdate><title>Quantum neuron with real weights</title><author>Monteiro, Cláudio A. ; Filho, Gustavo I.S. ; Costa, Matheus Hopper J. ; de Paula Neto, Fernando M. ; de Oliveira, Wilson R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c339t-12264836852d310f6dfb126861c79c2538ac7ad025053a0eac3bd5f64148ad523</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Artificial intelligence</topic><topic>Machine learning</topic><topic>Quantum artificial neurons</topic><topic>Quantum computing</topic><topic>Quantum machine learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Monteiro, Cláudio A.</creatorcontrib><creatorcontrib>Filho, Gustavo I.S.</creatorcontrib><creatorcontrib>Costa, Matheus Hopper J.</creatorcontrib><creatorcontrib>de Paula Neto, Fernando M.</creatorcontrib><creatorcontrib>de Oliveira, Wilson R.</creatorcontrib><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Neural networks</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Monteiro, Cláudio A.</au><au>Filho, Gustavo I.S.</au><au>Costa, Matheus Hopper J.</au><au>de Paula Neto, Fernando M.</au><au>de Oliveira, Wilson R.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Quantum neuron with real weights</atitle><jtitle>Neural networks</jtitle><date>2021-11</date><risdate>2021</risdate><volume>143</volume><spage>698</spage><epage>708</epage><pages>698-708</pages><issn>0893-6080</issn><eissn>1879-2782</eissn><abstract>This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical–quantum approach, considering the delta rule to update the values of the weights in an image database of three distinct patterns. We performed classical simulations and also executed experiments in an actual small-scale quantum processor. The results of the experiments show that the proposed quantum real neuron model has a good generalisation capacity, demonstrating better accuracy than the traditional binary quantum perceptron model.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.neunet.2021.07.034</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-7986-2695</orcidid><orcidid>https://orcid.org/0000-0002-3261-8265</orcidid><orcidid>https://orcid.org/0000-0003-4264-1124</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0893-6080
ispartof Neural networks, 2021-11, Vol.143, p.698-708
issn 0893-6080
1879-2782
language eng
recordid cdi_proquest_miscellaneous_2563427954
source ScienceDirect Journals (5 years ago - present)
subjects Artificial intelligence
Machine learning
Quantum artificial neurons
Quantum computing
Quantum machine learning
title Quantum neuron with real weights
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T11%3A33%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Quantum%20neuron%20with%20real%20weights&rft.jtitle=Neural%20networks&rft.au=Monteiro,%20Cl%C3%A1udio%20A.&rft.date=2021-11&rft.volume=143&rft.spage=698&rft.epage=708&rft.pages=698-708&rft.issn=0893-6080&rft.eissn=1879-2782&rft_id=info:doi/10.1016/j.neunet.2021.07.034&rft_dat=%3Cproquest_cross%3E2563427954%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2563427954&rft_id=info:pmid/&rft_els_id=S0893608021003051&rfr_iscdi=true