{"id":"https://openalex.org/W1546411676","doi":"https://doi.org/10.48550/arxiv.1306.0239","title":"Deep Learning using Linear Support Vector Machines","display_name":"Deep Learning using Linear Support Vector Machines","publication_year":2013,"publication_date":"2013-06-02","ids":{"openalex":"https://openalex.org/W1546411676","doi":"https://doi.org/10.48550/arxiv.1306.0239","mag":"1546411676"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1306.0239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1306.0239","pdf_url":"https://arxiv.org/pdf/1306.0239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1306.0239","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034956679","display_name":"Yichuan Tang","orcid":"https://orcid.org/0000-0003-1681-5944","observed_orcids":["https://orcid.org/0000-0003-1681-5944"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Tang, Yichuan","raw_affiliation_strings":["Department of Computer Science , University of Toronto. Toronto , Ontario , Canada","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Toronto. Toronto , Ontario , Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034956679"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1016,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.35109999775886536,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.35109999775886536,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.1906999945640564,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.13449999690055847,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-support-vector-machine","display_name":"linear support vector machine","score":0.9319999814033508},{"id":"https://openalex.org/keywords/softmax-replacement","display_name":"softmax replacement","score":0.6380000114440918},{"id":"https://openalex.org/keywords/margin-based-loss","display_name":"margin-based loss","score":0.921999990940094},{"id":"https://openalex.org/keywords/cross-entropy-loss","display_name":"cross-entropy loss","score":0.7940000295639038},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.6069999933242798},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"facial expression recognition","score":0.7329999804496765},{"id":"https://openalex.org/keywords/mnist","display_name":"MNIST","score":0.6499999761581421},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.996999979019165},{"id":"https://openalex.org/keywords/neural-network-classification","display_name":"neural network classification","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6506786346435547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5720292329788208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5157697200775146},{"id":"https://openalex.org/C92087593","wikidata":"https://www.wikidata.org/wiki/Q427389","display_name":"Vector (molecular biology)","level":4,"score":0.49534526467323303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4925449788570404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44775670766830444},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.135647714138031},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C40767141","wikidata":"https://www.wikidata.org/wiki/Q285697","display_name":"Recombinant DNA","level":3,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:1306.0239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1306.0239","pdf_url":"https://arxiv.org/pdf/1306.0239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.664.594","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.664.594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://deeplearning.net/wp-content/uploads/2013/03/dlsvm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.767.4102","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.767.4102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1306.0239.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1306.0239","doi":"https://doi.org/10.48550/arxiv.1306.0239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1306.0239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1306.0239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1306.0239","pdf_url":"https://arxiv.org/pdf/1306.0239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1546411676.pdf","grobid_xml":"https://content.openalex.org/works/W1546411676.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W205159212","https://openalex.org/W1574496672","https://openalex.org/W2087347434","https://openalex.org/W2097356275","https://openalex.org/W2099171762","https://openalex.org/W2100341991","https://openalex.org/W2103359087","https://openalex.org/W2112504244","https://openalex.org/W2118858186","https://openalex.org/W2130325614","https://openalex.org/W2133282586","https://openalex.org/W2138621090","https://openalex.org/W2147860648","https://openalex.org/W2152424459","https://openalex.org/W2156909104","https://openalex.org/W2159291644","https://openalex.org/W2163605009","https://openalex.org/W2176028050","https://openalex.org/W2546302380"],"related_works":["https://openalex.org/W4300841382","https://openalex.org/W825525975","https://openalex.org/W3039380052","https://openalex.org/W3000180257","https://openalex.org/W2944639158","https://openalex.org/W6931052376","https://openalex.org/W4367299702","https://openalex.org/W2470008419","https://openalex.org/W2766557427","https://openalex.org/W3008342523"],"abstract_inverted_index":{"Recently,":[0],"fully-connected":[1],"and":[2,28,46,90,118],"convolutional":[3],"neural":[4,88],"networks":[5],"have":[6,83],"been":[7,84],"trained":[8],"to":[9],"achieve":[10],"state-of-the-art":[11],"performance":[12],"on":[13,111],"a":[14,55,66,73],"wide":[15],"variety":[16],"of":[17,34,60,77,87],"tasks":[18],"such":[19],"as":[20],"speech":[21],"recognition,":[22],"image":[23],"classification,":[24],"natural":[25],"language":[26],"processing,":[27],"bioinformatics.":[29],"For":[30],"classification":[31],"tasks,":[32],"most":[33],"these":[35],"\"deep":[36],"learning\"":[37],"models":[38],"employ":[39],"the":[40,62,78,119],"softmax":[41,63,104],"activation":[42],"function":[43],"for":[44],"prediction":[45],"minimize":[47],"cross-entropy":[48,79],"loss.":[49,80],"In":[50],"this":[51],"paper,":[52],"we":[53],"demonstrate":[54],"small":[56],"but":[57],"consistent":[58],"advantage":[59],"replacing":[61,103],"layer":[64],"with":[65,105],"linear":[67,106],"support":[68],"vector":[69],"machine.":[70],"Learning":[71,123],"minimizes":[72],"margin-based":[74],"loss":[75],"instead":[76],"While":[81],"there":[82],"various":[85],"combinations":[86],"nets":[89],"SVMs":[91,107],"in":[92],"prior":[93],"art,":[94],"our":[95],"results":[96],"using":[97],"L2-SVMs":[98],"show":[99],"that":[100],"by":[101],"simply":[102],"gives":[108],"significant":[109],"gains":[110],"popular":[112],"deep":[113],"learning":[114],"datasets":[115],"MNIST,":[116],"CIFAR-10,":[117],"ICML":[120],"2013":[121],"Representation":[122],"Workshop's":[124],"face":[125],"expression":[126],"recognition":[127],"challenge.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":68},{"year":2023,"cited_by_count":95},{"year":2022,"cited_by_count":86},{"year":2021,"cited_by_count":128},{"year":2020,"cited_by_count":153},{"year":2019,"cited_by_count":134},{"year":2018,"cited_by_count":108},{"year":2017,"cited_by_count":82},{"year":2016,"cited_by_count":56},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}