{"id":"https://openalex.org/W2518187001","doi":"https://doi.org/10.1109/icpr.2016.7900183","title":"Faster training of very deep networks via p-norm gates","display_name":"Faster training of very deep networks via p-norm gates","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2518187001","doi":"https://doi.org/10.1109/icpr.2016.7900183","mag":"2518187001"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7900183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","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/1608.03639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102943268","display_name":"Trang Pham","orcid":"https://orcid.org/0000-0003-3702-7963"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Trang Pham","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085471517","display_name":"Truyen Tran","orcid":"https://orcid.org/0000-0001-6531-8907"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Truyen Tran","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036447132","display_name":"Dinh Phung","orcid":"https://orcid.org/0000-0002-9977-8247"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dinh Phung","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045540854","display_name":"Svetha Venkatesh","orcid":"https://orcid.org/0000-0001-8675-6631"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Svetha Venkatesh","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102943268"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":0.28187688,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82731716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3542","last_page":"3547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9979000091552734,"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":0.9965000152587891,"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/gating","display_name":"Gating","score":0.7488692998886108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405543923377991},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7117258310317993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6329134106636047},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5956432223320007},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5320352911949158},{"id":"https://openalex.org/keywords/information-flow","display_name":"Information flow","score":0.5091964602470398},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.44928881525993347},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44467759132385254},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4381120204925537},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42811548709869385},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4111182689666748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3982076048851013},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2759935259819031},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2003026008605957},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.12688103318214417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09159740805625916}],"concepts":[{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.7488692998886108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405543923377991},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7117258310317993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6329134106636047},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5956432223320007},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5320352911949158},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.5091964602470398},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.44928881525993347},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44467759132385254},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4381120204925537},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42811548709869385},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4111182689666748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3982076048851013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2759935259819031},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2003026008605957},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.12688103318214417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09159740805625916},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icpr.2016.7900183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1608.03639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.03639","pdf_url":"https://arxiv.org/pdf/1608.03639","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":null,"raw_type":"text"},{"id":"mag:2518187001","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1608.03639.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":"pmh:oai:dro.deakin.edu.au:DU:30096794","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402457","display_name":"Deakin Research Online (Deakin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.1608.03639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1608.03639","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:1608.03639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.03639","pdf_url":"https://arxiv.org/pdf/1608.03639","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2518187001.pdf","grobid_xml":"https://content.openalex.org/works/W2518187001.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1810943226","https://openalex.org/W1899249567","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2131494463","https://openalex.org/W2140833774","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2178103884","https://openalex.org/W2194775991","https://openalex.org/W2255847468","https://openalex.org/W2949888546","https://openalex.org/W2950035161","https://openalex.org/W2950621961","https://openalex.org/W2951559648","https://openalex.org/W2964199361","https://openalex.org/W3037950864","https://openalex.org/W4231109964","https://openalex.org/W6626481562","https://openalex.org/W6631636882","https://openalex.org/W6638273328","https://openalex.org/W6639736602","https://openalex.org/W6640212811","https://openalex.org/W6640598943","https://openalex.org/W6679436768","https://openalex.org/W6679844565","https://openalex.org/W6680887930","https://openalex.org/W6685330469","https://openalex.org/W6687483927","https://openalex.org/W6696761078"],"related_works":["https://openalex.org/W2963064784","https://openalex.org/W3086425440","https://openalex.org/W2769858569","https://openalex.org/W2978610144","https://openalex.org/W2896827527","https://openalex.org/W2959071218","https://openalex.org/W2903120399","https://openalex.org/W2749432513","https://openalex.org/W2966950562","https://openalex.org/W2892279525","https://openalex.org/W2962677625","https://openalex.org/W2769315836","https://openalex.org/W2739515247","https://openalex.org/W2593303827","https://openalex.org/W2422848620","https://openalex.org/W3189972411","https://openalex.org/W3201909459","https://openalex.org/W2905878277","https://openalex.org/W3036733868","https://openalex.org/W3186421600"],"abstract_inverted_index":{"A":[0],"major":[1],"contributing":[2],"factor":[3],"to":[4,21],"the":[5,95,100,122,153,159],"recent":[6,40],"advances":[7],"in":[8,38,62,74,93,99,134],"deep":[9,64],"neural":[10],"networks":[11,65],"is":[12,25,90],"structural":[13],"units":[14],"that":[15,29,152],"let":[16],"sensory":[17],"information":[18],"and":[19,47,49,56,69,81,117,138,148],"gradients":[20],"propagate":[22],"easily.":[23],"Gating":[24],"one":[26],"such":[27,44,52],"structure":[28],"acts":[30],"as":[31,45,53,118,141],"a":[32,108,119],"flow":[33,116],"control.":[34],"Gates":[35],"are":[36],"employed":[37],"many":[39],"state-of-the-art":[41],"recurrent":[42],"models":[43,51],"LSTM":[46],"GRU,":[48,135],"feedforward":[50],"Residual":[54,79,139],"Nets":[55,140],"Highway":[57,136],"Networks.":[58],"This":[59,125],"enables":[60],"learning":[61,101,123,160],"very":[63],"with":[66,78,86],"hundred":[67],"layers":[68],"helps":[70,157],"achieve":[71],"record-breaking":[72],"results":[73],"vision":[75],"(e.g.,":[76,83],"ImageNet":[77],"Nets)":[80],"NLP":[82],"machine":[84],"translation":[85],"GRU).":[87],"However,":[88],"there":[89],"limited":[91],"work":[92],"analysing":[94],"role":[96],"of":[97],"gating":[98,111,130,155],"process.":[102],"In":[103],"this":[104],"paper,":[105],"we":[106],"propose":[107],"flexible":[109],"$p$-norm":[110],"scheme,":[112],"which":[113],"allows":[114],"user-controllable":[115],"consequence,":[120],"improve":[121,158],"speed.":[124],"scheme":[126,156],"subsumes":[127],"other":[128],"existing":[129],"schemes,":[131],"including":[132],"those":[133],"Networks":[137],"special":[142],"cases.":[143],"Experiments":[144],"on":[145],"large":[146],"sequence":[147],"vector":[149],"datasets":[150],"demonstrate":[151],"proposed":[154],"speed":[161],"significantly":[162],"without":[163],"extra":[164],"overhead.":[165]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}