Approximation of functions from Korobov spaces by deep convolutional neural networks
The efficiency of deep convolutional neural networks (DCNNs) has been demonstrated empirically in many practical applications. In this paper, we establish a theory for approximating functions from Korobov spaces by DCNNs. It verifies rigorously the efficiency of DCNNs in approximating functions of m...
Gespeichert in:
| Veröffentlicht in: | Advances in computational mathematics 2022-12, Vol.48 (6), Article 84 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 6 |
| container_start_page | |
| container_title | Advances in computational mathematics |
| container_volume | 48 |
| creator | Mao, Tong Zhou, Ding-Xuan |
| description | The efficiency of deep convolutional neural networks (DCNNs) has been demonstrated empirically in many practical applications. In this paper, we establish a theory for approximating functions from Korobov spaces by DCNNs. It verifies rigorously the efficiency of DCNNs in approximating functions of many variables with some variable structures and their abilities in overcoming the curse of dimensionality. |
| doi_str_mv | 10.1007/s10444-022-09991-x |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2747917342</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2747917342</sourcerecordid><originalsourceid>FETCH-LOGICAL-c363t-676f97382c546c2611f8f7ad29548f0940e8c69ef6c91cb222f65a3c02c1b2383</originalsourceid><addsrcrecordid>eNp9UMFKAzEUDKJgrf6Ap4DnaPKSTTbHUtSKBS_1HHbTRFrbzZrs1vbvTbuCN08z8GaGN4PQLaP3jFL1kBgVQhAKQKjWmpH9GRqxQgHR-XCeOWWaKCbLS3SV0ppSqqUqRmgxadsY9qtt1a1Cg4PHvm_skSfsY9ji1xBDHXY4tZV1CdcHvHSuxTY0u7Dpj8JqgxvXxxN03yF-pmt04atNcje_OEbvT4-L6YzM355fppM5sVzyjkglvVa8BFsIaUEy5kuvqiXoQpSeakFdaaV2XlrNbA0AXhYVtxQsq4GXfIzuhtxc4at3qTPr0Mf8UDKghNJMcQFZBYPKxpBSdN60MfeNB8OoOa5nhvVMXs-c1jP7bOKDKWVx8-HiX_Q_rh9WxnOk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2747917342</pqid></control><display><type>article</type><title>Approximation of functions from Korobov spaces by deep convolutional neural networks</title><source>SpringerNature Journals</source><creator>Mao, Tong ; Zhou, Ding-Xuan</creator><creatorcontrib>Mao, Tong ; Zhou, Ding-Xuan</creatorcontrib><description>The efficiency of deep convolutional neural networks (DCNNs) has been demonstrated empirically in many practical applications. In this paper, we establish a theory for approximating functions from Korobov spaces by DCNNs. It verifies rigorously the efficiency of DCNNs in approximating functions of many variables with some variable structures and their abilities in overcoming the curse of dimensionality.</description><identifier>ISSN: 1019-7168</identifier><identifier>EISSN: 1572-9044</identifier><identifier>DOI: 10.1007/s10444-022-09991-x</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Approximation ; Artificial neural networks ; Computational mathematics ; Computational Mathematics and Numerical Analysis ; Computational Science and Engineering ; Mathematical analysis ; Mathematical and Computational Biology ; Mathematical Modeling and Industrial Mathematics ; Mathematics ; Mathematics and Statistics ; Visualization</subject><ispartof>Advances in computational mathematics, 2022-12, Vol.48 (6), Article 84</ispartof><rights>The Author(s) 2022</rights><rights>The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c363t-676f97382c546c2611f8f7ad29548f0940e8c69ef6c91cb222f65a3c02c1b2383</citedby><cites>FETCH-LOGICAL-c363t-676f97382c546c2611f8f7ad29548f0940e8c69ef6c91cb222f65a3c02c1b2383</cites><orcidid>0000-0003-0224-9216</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s10444-022-09991-x$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s10444-022-09991-x$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>315,781,785,27928,27929,41492,42561,51323</link.rule.ids></links><search><creatorcontrib>Mao, Tong</creatorcontrib><creatorcontrib>Zhou, Ding-Xuan</creatorcontrib><title>Approximation of functions from Korobov spaces by deep convolutional neural networks</title><title>Advances in computational mathematics</title><addtitle>Adv Comput Math</addtitle><description>The efficiency of deep convolutional neural networks (DCNNs) has been demonstrated empirically in many practical applications. In this paper, we establish a theory for approximating functions from Korobov spaces by DCNNs. It verifies rigorously the efficiency of DCNNs in approximating functions of many variables with some variable structures and their abilities in overcoming the curse of dimensionality.</description><subject>Approximation</subject><subject>Artificial neural networks</subject><subject>Computational mathematics</subject><subject>Computational Mathematics and Numerical Analysis</subject><subject>Computational Science and Engineering</subject><subject>Mathematical analysis</subject><subject>Mathematical and Computational Biology</subject><subject>Mathematical Modeling and Industrial Mathematics</subject><subject>Mathematics</subject><subject>Mathematics and Statistics</subject><subject>Visualization</subject><issn>1019-7168</issn><issn>1572-9044</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><recordid>eNp9UMFKAzEUDKJgrf6Ap4DnaPKSTTbHUtSKBS_1HHbTRFrbzZrs1vbvTbuCN08z8GaGN4PQLaP3jFL1kBgVQhAKQKjWmpH9GRqxQgHR-XCeOWWaKCbLS3SV0ppSqqUqRmgxadsY9qtt1a1Cg4PHvm_skSfsY9ji1xBDHXY4tZV1CdcHvHSuxTY0u7Dpj8JqgxvXxxN03yF-pmt04atNcje_OEbvT4-L6YzM355fppM5sVzyjkglvVa8BFsIaUEy5kuvqiXoQpSeakFdaaV2XlrNbA0AXhYVtxQsq4GXfIzuhtxc4at3qTPr0Mf8UDKghNJMcQFZBYPKxpBSdN60MfeNB8OoOa5nhvVMXs-c1jP7bOKDKWVx8-HiX_Q_rh9WxnOk</recordid><startdate>20221201</startdate><enddate>20221201</enddate><creator>Mao, Tong</creator><creator>Zhou, Ding-Xuan</creator><general>Springer US</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-0224-9216</orcidid></search><sort><creationdate>20221201</creationdate><title>Approximation of functions from Korobov spaces by deep convolutional neural networks</title><author>Mao, Tong ; Zhou, Ding-Xuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c363t-676f97382c546c2611f8f7ad29548f0940e8c69ef6c91cb222f65a3c02c1b2383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Approximation</topic><topic>Artificial neural networks</topic><topic>Computational mathematics</topic><topic>Computational Mathematics and Numerical Analysis</topic><topic>Computational Science and Engineering</topic><topic>Mathematical analysis</topic><topic>Mathematical and Computational Biology</topic><topic>Mathematical Modeling and Industrial Mathematics</topic><topic>Mathematics</topic><topic>Mathematics and Statistics</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mao, Tong</creatorcontrib><creatorcontrib>Zhou, Ding-Xuan</creatorcontrib><collection>Springer Nature OA/Free Journals</collection><collection>CrossRef</collection><jtitle>Advances in computational mathematics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mao, Tong</au><au>Zhou, Ding-Xuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Approximation of functions from Korobov spaces by deep convolutional neural networks</atitle><jtitle>Advances in computational mathematics</jtitle><stitle>Adv Comput Math</stitle><date>2022-12-01</date><risdate>2022</risdate><volume>48</volume><issue>6</issue><artnum>84</artnum><issn>1019-7168</issn><eissn>1572-9044</eissn><abstract>The efficiency of deep convolutional neural networks (DCNNs) has been demonstrated empirically in many practical applications. In this paper, we establish a theory for approximating functions from Korobov spaces by DCNNs. It verifies rigorously the efficiency of DCNNs in approximating functions of many variables with some variable structures and their abilities in overcoming the curse of dimensionality.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s10444-022-09991-x</doi><orcidid>https://orcid.org/0000-0003-0224-9216</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1019-7168 |
| ispartof | Advances in computational mathematics, 2022-12, Vol.48 (6), Article 84 |
| issn | 1019-7168 1572-9044 |
| language | eng |
| recordid | cdi_proquest_journals_2747917342 |
| source | SpringerNature Journals |
| subjects | Approximation Artificial neural networks Computational mathematics Computational Mathematics and Numerical Analysis Computational Science and Engineering Mathematical analysis Mathematical and Computational Biology Mathematical Modeling and Industrial Mathematics Mathematics Mathematics and Statistics Visualization |
| title | Approximation of functions from Korobov spaces by deep convolutional neural networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-16T17%3A27%3A20IST&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=Approximation%20of%20functions%20from%20Korobov%20spaces%20by%20deep%20convolutional%20neural%20networks&rft.jtitle=Advances%20in%20computational%20mathematics&rft.au=Mao,%20Tong&rft.date=2022-12-01&rft.volume=48&rft.issue=6&rft.artnum=84&rft.issn=1019-7168&rft.eissn=1572-9044&rft_id=info:doi/10.1007/s10444-022-09991-x&rft_dat=%3Cproquest_cross%3E2747917342%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=2747917342&rft_id=info:pmid/&rfr_iscdi=true |