{"id":"https://openalex.org/W2774680561","doi":"https://doi.org/10.1109/acssc.2018.8645094","title":"Data Dropout in Arbitrary Basis for Deep Network Regularization","display_name":"Data Dropout in Arbitrary Basis for Deep Network Regularization","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2774680561","doi":"https://doi.org/10.1109/acssc.2018.8645094","mag":"2774680561"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2018.8645094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645094","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.00891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101657195","display_name":"Mostafa Rahmani","orcid":"https://orcid.org/0000-0002-4140-383X"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mostafa Rahmani","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003612688","display_name":"George Atia","orcid":"https://orcid.org/0000-0001-7958-9855"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George K. Atia","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101657195"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00591483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9983000159263611,"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/T10057","display_name":"Face and Expression Recognition","score":0.9952999949455261,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.8201264142990112},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7994881868362427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6846176385879517},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4711769223213196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580906331539154},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.45440950989723206},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44843241572380066},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4446057677268982},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4432607889175415},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41982612013816833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.377696692943573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24910083413124084}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.8201264142990112},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7994881868362427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6846176385879517},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4711769223213196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580906331539154},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.45440950989723206},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44843241572380066},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4446057677268982},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4432607889175415},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41982612013816833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.377696692943573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24910083413124084},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/acssc.2018.8645094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645094","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.00891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.00891","pdf_url":"https://arxiv.org/pdf/1712.00891","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2774680561","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1712.00891.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1712.00891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.00891","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.00891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.00891","pdf_url":"https://arxiv.org/pdf/1712.00891","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3157310737","display_name":"CAREER: Inference-Driven Data Processing and Acquisition: Scalability, Robustness and Control","funder_award_id":"1552497","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G659905212","display_name":null,"funder_award_id":"CCF-1552497","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2774680561.pdf","grobid_xml":"https://content.openalex.org/works/W2774680561.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1034159276","https://openalex.org/W1849277567","https://openalex.org/W1979482308","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W6601425427","https://openalex.org/W6604254268","https://openalex.org/W6629368666","https://openalex.org/W6629389771","https://openalex.org/W6631160641","https://openalex.org/W6631190155","https://openalex.org/W6635590879","https://openalex.org/W6640036494","https://openalex.org/W6674330103","https://openalex.org/W6677190780","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6679955943","https://openalex.org/W6682824805","https://openalex.org/W6692201896","https://openalex.org/W6713132643","https://openalex.org/W6725739302","https://openalex.org/W6729344799","https://openalex.org/W6730362966"],"related_works":["https://openalex.org/W2963704822","https://openalex.org/W3042655050","https://openalex.org/W3037661305","https://openalex.org/W2913407569","https://openalex.org/W2803858435","https://openalex.org/W3163957830","https://openalex.org/W2969404624","https://openalex.org/W3194674358","https://openalex.org/W2926362642","https://openalex.org/W2984938990","https://openalex.org/W2998675825","https://openalex.org/W2922944537","https://openalex.org/W1652178237","https://openalex.org/W2947603240","https://openalex.org/W2914317573","https://openalex.org/W2945799378","https://openalex.org/W2737836580","https://openalex.org/W3195600832","https://openalex.org/W2899008792","https://openalex.org/W2899494786"],"abstract_inverted_index":{"In":[0,62,88],"training":[1,25,60],"deep":[2],"networks":[3],"with":[4,20],"high":[5],"capacity,":[6],"it":[7],"is":[8,28,86,97,107],"important":[9],"to":[10,33,56,99,131,182],"ensure":[11],"that":[12,140,160,187],"the":[13,24,35,44,47,51,59,78,84,89,94,114,124,141,155],"trained":[14],"network":[15],"works":[16],"well":[17],"when":[18],"presented":[19,136],"new":[21,66,152,176],"inputs":[22],"outside":[23],"dataset.":[26],"Dropout":[27,150],"an":[29,110],"effective":[30],"regularization":[31,68],"technique":[32,69,126,143],"boost":[34],"network's":[36],"generalization":[37],"in":[38,70,109],"which":[39,71,93],"a":[40,65,74,101,121,145,175],"random":[41,75,104],"subset":[42],"of":[43,46,77,92,157,180],"elements":[45],"given":[48],"data":[49,79,105],"and":[50,172],"extracted":[52],"features":[53],"are":[54],"set":[55],"zero":[57],"during":[58],"process.":[61],"this":[63],"paper,":[64],"randomized":[67],"we":[72,161],"withhold":[73],"part":[76],"without":[80],"necessarily":[81],"turning":[82],"off":[83],"neurons/data-elements":[85],"proposed.":[87],"proposed":[90,125,142],"method,":[91],"conventional":[95],"dropout":[96,106],"shown":[98],"be":[100,128],"special":[102],"case,":[103],"performed":[108],"arbitrary":[111],"basis,":[112],"hence":[113],"designation":[115],"Generalized":[116,149],"Dropout.":[117],"We":[118],"also":[119],"present":[120],"framework":[122],"whereby":[123],"can":[127,162],"applied":[129],"efficiently":[130],"convolutional":[132],"neural":[133],"networks.":[134],"The":[135],"numerical":[137],"experiments":[138],"demonstrate":[139],"yields":[144],"notable":[146],"performance":[147,165,190],"gain.":[148,191],"provides":[151],"insight":[153],"into":[154],"idea":[156],"dropout,":[158],"shows":[159],"achieve":[163,188],"different":[164,169],"gains":[166],"by":[167],"using":[168],"bases":[170,185],"matrices,":[171],"opens":[173],"up":[174],"research":[177],"question":[178],"as":[179],"how":[181],"choose":[183],"optimal":[184],"matrices":[186],"maximal":[189]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}