{"id":"https://openalex.org/W2810172011","doi":"https://doi.org/10.48550/arxiv.1806.09141","title":"Constructing Deep Neural Networks by Bayesian Network Structure Learning","display_name":"Constructing Deep Neural Networks by Bayesian Network Structure Learning","publication_year":2018,"publication_date":"2018-06-24","ids":{"openalex":"https://openalex.org/W2810172011","doi":"https://doi.org/10.48550/arxiv.1806.09141","mag":"2810172011"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1806.09141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.09141","pdf_url":"https://arxiv.org/pdf/1806.09141","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.09141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044277691","display_name":"Raanan Y. Rohekar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohekar, Raanan Y.","raw_affiliation_strings":["Intel AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel AI Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056922604","display_name":"Shami Nisimov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nisimov, Shami","raw_affiliation_strings":["Intel AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel AI Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042429340","display_name":"Yaniv Gurwicz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gurwicz, Yaniv","raw_affiliation_strings":["Intel AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel AI Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069937565","display_name":"G. Koren","orcid":"https://orcid.org/0000-0002-0773-8775","observed_orcids":["https://orcid.org/0000-0002-0773-8775"]},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koren, Guy","raw_affiliation_strings":["Intel AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel AI Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023367765","display_name":"Gal Novik","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Novik, Gal","raw_affiliation_strings":["Intel AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel AI Labs","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"3051","last_page":"3062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.948199987411499,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.948199987411499,"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/T10320","display_name":"Neural Networks and Applications","score":0.026599999517202377,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.013899999670684338,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bayesian-network-structure-learning","display_name":"Bayesian network structure learning","score":0.9419999718666077},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"conditional independence","score":0.7039999961853027},{"id":"https://openalex.org/keywords/network-depth","display_name":"network depth","score":0.578000009059906},{"id":"https://openalex.org/keywords/latent-variables","display_name":"latent variables","score":0.7350000143051147},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.7549999952316284},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.5170000195503235},{"id":"https://openalex.org/keywords/dense-networks","display_name":"dense networks","score":0.6549999713897705}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7693937420845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920075416564941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6847150325775146},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5506566762924194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5122079253196716},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49799537658691406},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4737035930156708},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4665498435497284},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4618040919303894},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.43772467970848083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43748199939727783},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3824117183685303},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31272512674331665}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1806.09141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.09141","pdf_url":"https://arxiv.org/pdf/1806.09141","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":"doi:10.48550/arxiv.1806.09141","doi":"https://doi.org/10.48550/arxiv.1806.09141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.09141","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":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2963989804","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.09141.pdf","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":null,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.09141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.09141","pdf_url":"https://arxiv.org/pdf/1806.09141","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":[],"sustainable_development_goals_aurora":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1866230956","https://openalex.org/W1935978687","https://openalex.org/W2008906462","https://openalex.org/W2083380015","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2098694378","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2135181320","https://openalex.org/W2136922672","https://openalex.org/W2152332944","https://openalex.org/W2152424459","https://openalex.org/W2155541015","https://openalex.org/W2158899491","https://openalex.org/W2159291411","https://openalex.org/W2167215970","https://openalex.org/W2178031510","https://openalex.org/W2194775991","https://openalex.org/W2253535400","https://openalex.org/W2276295848","https://openalex.org/W2335728318","https://openalex.org/W2417988721","https://openalex.org/W2463256602","https://openalex.org/W2534788641","https://openalex.org/W2546302380","https://openalex.org/W2553303224","https://openalex.org/W2593744649","https://openalex.org/W2594529350","https://openalex.org/W2736941579","https://openalex.org/W2771111398","https://openalex.org/W2949117887","https://openalex.org/W2951886768","https://openalex.org/W2952278564","https://openalex.org/W2963140066","https://openalex.org/W2963446712","https://openalex.org/W2963674932","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2964299589","https://openalex.org/W2979006918","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W1493875009","https://openalex.org/W4241564561"],"abstract_inverted_index":{"We":[0,13,88,108],"introduce":[1],"a":[2,15,58,75,85,144,152],"principled":[3],"approach":[4],"for":[5,18],"unsupervised":[6],"structure":[7,55,63,140],"learning":[8,56,69,141],"of":[9,40,52,60,67,121],"deep":[10],"neural":[11,53],"networks.":[12],"propose":[14],"new":[16],"interpretation":[17],"depth":[19,39],"and":[20,82,119,148],"inter-layer":[21],"connectivity":[22],"where":[23],"conditional":[24],"independencies":[25],"in":[26,33,97,103],"the":[27,34,38,41,50,70,94,98,104,115],"input":[28],"distribution":[29],"are":[30,101],"encoded":[31],"hierarchically":[32],"network":[35,42,54,62],"structure.":[36],"Thus,":[37],"is":[43],"determined":[44],"inherently.":[45],"The":[46],"proposed":[47],"method":[48],"casts":[49],"problem":[51,59],"as":[57],"Bayesian":[61],"learning.":[64],"Then,":[65],"instead":[66],"directly":[68],"discriminative":[71,86,106],"structure,":[72],"it":[73],"learns":[74],"generative":[76,99],"graph,":[77],"constructs":[78,84],"its":[79],"stochastic":[80],"inverse,":[81],"then":[83],"graph.":[87,107],"prove":[89],"that":[90,114],"conditional-dependency":[91],"relations":[92],"among":[93],"latent":[95],"variables":[96],"graph":[100],"preserved":[102],"class-conditional":[105],"demonstrate":[109],"on":[110,136,151],"image":[111],"classification":[112,134],"benchmarks":[113],"deepest":[116],"layers":[117],"(convolutional":[118],"dense)":[120],"common":[122],"networks":[123],"can":[124],"be":[125],"replaced":[126],"by":[127],"significantly":[128],"smaller":[129],"learned":[130],"structures,":[131],"while":[132],"maintaining":[133],"accuracy---state-of-the-art":[135],"tested":[137],"benchmarks.":[138],"Our":[139],"algorithm":[142],"requires":[143],"small":[145],"computational":[146],"cost":[147],"runs":[149],"efficiently":[150],"standard":[153],"desktop":[154],"CPU.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}