{"id":"https://openalex.org/W1067145707","doi":"https://doi.org/10.1145/2740908.2741982","title":"Deep Learning for the Web","display_name":"Deep Learning for the Web","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W1067145707","doi":"https://doi.org/10.1145/2740908.2741982","mag":"1067145707"},"language":"en","primary_location":{"id":"doi:10.1145/2740908.2741982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077832834","display_name":"Kyomin Jung","orcid":"https://orcid.org/0000-0003-2547-7051"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyomin Jung","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050928023","display_name":"Byoung\u2010Tak Zhang","orcid":"https://orcid.org/0000-0001-9890-0389"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung-Tak Zhang","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Prasenjit Mitra","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077832834"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74516975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1525","last_page":"1526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9959999918937683,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8110364079475403},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7713156938552856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6480553150177002},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6066509485244751},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42328760027885437},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3495906591415405},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3408195674419403},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1442083716392517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110364079475403},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7713156938552856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6480553150177002},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6066509485244751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42328760027885437},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3495906591415405},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3408195674419403},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1442083716392517}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2740908.2741982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W22861983","https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2136189984","https://openalex.org/W2136922672","https://openalex.org/W2143612262","https://openalex.org/W2145287260","https://openalex.org/W2163605009","https://openalex.org/W2280554126","https://openalex.org/W2604272474","https://openalex.org/W2963542991","https://openalex.org/W2981785444"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084","https://openalex.org/W3003361536"],"abstract_inverted_index":{"Deep":[0,92],"learning":[1,5,40,90,93,127,143,149,154,162,236,310,470,496],"is":[2,221,271],"a":[3,95,213,272,393,487,494],"machine":[4,235],"technology":[6],"that":[7,43,207],"automatically":[8],"extracts":[9],"higher-level":[10],"representations":[11,27,375],"from":[12,526],"raw":[13],"data":[14,64,116,172,175,181,239,298,530,535],"by":[15,84,110,392],"stacking":[16,23],"multiple":[17],"layers":[18],"of":[19,28,38,61,102,125,141,160,188,199,216,247,256,275,289,304,334,360,396,467,475,490,508,516],"neuron-like":[20],"units.":[21],"The":[22,219,244,250,427,505],"allows":[24],"for":[25,151,163,241,312,376,444,498,537],"extracting":[26],"increasingly-complex":[29],"features":[30],"without":[31],"time-consuming,":[32],"offline":[33],"feature":[34],"engineering.":[35],"Recent":[36],"success":[37],"deep":[39,89,126,142,153,161,281,313,335,340,349,445,469,495,517],"has":[41,94],"shown":[42],"it":[44],"outperforms":[45],"state-of-the-art":[46],"systems":[47,66,83,109],"in":[48,185,211,234,295,452,463,472],"image":[49,164],"processing,":[50,167],"voice":[51,81],"recognition,":[52],"web":[53,104,107,529],"search,":[54],"recommendation":[55],"systems,":[56],"etc":[57],"[1].":[58],"A":[59],"lot":[60],"industrial-scale":[62],"big":[63,115,238],"processing":[65],"including":[67,280,337,421],"IBM":[68],"Watson's":[69],"Jeopardy":[70],"Contest":[71],"2011,":[72],"Google":[73,85],"Now,":[74],"Facebook's":[75],"face":[76],"recognition":[77,82,525],"system,":[78],"and":[79,86,105,112,138,144,148,165,170,177,197,205,237,259,316,325,348,378,424,449,458,501,523,532],"the":[80,100,103,106,118,123,136,146,186,194,228,254,265,301,305,309,353,361,385,397,405,431,465,473,483,509],"Microsoft":[87],"use":[88],"[2][3][6].":[91],"huge":[96],"potential":[97],"to":[98,223,407,418,435,492],"improve":[99],"intelligence":[101],"service":[108],"efficiently":[111],"effectively":[113],"mining":[114],"on":[117,409],"Web[4][5].":[119],"This":[120],"tutorial":[121,220,245,510],"provides":[122],"basics":[124,255],"as":[128,130,320,371,373,440,456],"well":[129,372],"its":[131,416],"key":[132,195],"applications.":[133],"We":[134,156,191,284,329,380,460],"give":[135],"motivation":[137],"underlying":[139],"ideas":[140],"describe":[145,308,331],"architectures":[147],"algorithms":[150,311],"various":[152,296,332,476],"models.":[155],"also":[157],"cover":[158,512],"applications":[159,417,466],"video":[166],"natural":[168],"language":[169],"text":[171],"analysis,":[173],"social":[174,477],"analytics,":[176,531],"wearable":[178],"IoT":[179],"sensor":[180,534],"with":[182],"an":[183],"emphasis":[184],"domain":[187],"Web":[189,217,242,297],"systems.":[190],"will":[192,285,414,461,511],"deliver":[193],"insight":[196],"understanding":[198,489],"these":[200,290,468],"techniques,":[201],"using":[202],"graphical":[203],"illustrations":[204],"examples":[206,515],"could":[208],"be":[209,293,390],"important":[210],"analyzing":[212],"large":[214],"amount":[215],"data.":[218,243,479],"prepared":[222],"attract":[224],"general":[225],"audience":[226,484],"at":[227],"WWW":[229],"Conference,":[230],"who":[231],"are":[232],"interested":[233],"analysis":[240,420,474],"consists":[246],"five":[248],"parts.":[249],"first":[251,381],"part":[252,303,429,507],"presents":[253],"neural":[257,278,282,314,345,363,387,432],"networks,":[258,364],"their":[260],"structures.":[261,411],"Then":[262,412],"we":[263,307,356,413],"explain":[264,462],"training":[266,276,384],"algorithm":[267,399,406],"via":[268],"backpropagation,":[269],"which":[270,365],"common":[273],"method":[274],"artificial":[277],"networks":[279,315,342,346,433],"networks.":[283],"emphasize":[286],"how":[287,383,491],"each":[288],"concepts":[291],"can":[292,366,389],"used":[294,434],"analysis.":[299,426],"In":[300,352],"second":[302],"tutorial,":[306],"related":[317],"ideas,":[318],"such":[319,439,455],"contrastive":[321],"divergence,":[322],"wake-sleep":[323],"algorithms,":[324],"Monte":[326],"Carlo":[327],"simulation.":[328],"then":[330],"kinds":[333],"architectures,":[336],"stacked":[338],"autoencoders,":[339],"belief":[341],"[7],":[343],"convolutional":[344],"[8],":[347],"hypernetworks":[350],"[9].":[351],"third":[354],"part,":[355],"present":[357,415],"more":[358],"details":[359],"recursive":[362,386],"learn":[367],"structured":[368],"tree":[369,410],"outputs":[370],"vector":[374],"phrases":[377],"sentences.":[379],"show":[382],"network":[388,478],"achieved":[391],"modified":[394],"version":[395],"back-propagation":[398],"introduced":[400],"before.":[401],"These":[402,519],"modifications":[403],"allow":[404],"work":[408],"sentence":[419,500],"POS":[422],"tagging,":[423],"sentiment":[425],"fourth":[428],"discusses":[430],"generate":[436],"word":[437],"embeddings,":[438],"Word2Vec":[441],"[10],":[442],"DSSM":[443],"semantic":[446],"similarity":[447],"[11],":[448],"object":[450,521],"detection":[451],"images":[453],"[12],":[454],"GoogLeNet,":[457],"AlexNet.":[459],"detail":[464],"techniques":[471],"By":[480],"this":[481],"point,":[482],"should":[485],"have":[486],"clear":[488],"build":[493],"system":[497],"word,":[499],"document":[502],"level":[503],"tasks.":[504],"fifth":[506],"other":[513],"application":[514],"learning.":[518],"include":[520],"segmentation":[522],"action":[524],"videos":[527],"[9],":[528],"wearable/IoT":[533],"modeling":[536],"smart":[538],"services.":[539]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}