{"id":"https://openalex.org/W2997356057","doi":"https://doi.org/10.1109/tpami.2020.3010201","title":"A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks","display_name":"A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks","publication_year":2020,"publication_date":"2020-07-17","ids":{"openalex":"https://openalex.org/W2997356057","doi":"https://doi.org/10.1109/tpami.2020.3010201","mag":"2997356057","pmid":"https://pubmed.ncbi.nlm.nih.gov/32750821"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2020.3010201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3010201","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.00254","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037216840","display_name":"Zhaodong Chen","orcid":"https://orcid.org/0000-0001-9601-4586"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Zhaodong Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","Department of Precision Instrument, Center for Brain Inspired Computing Research, Beijing Innovation Center for Future Chip, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"Department of Precision Instrument, Center for Brain Inspired Computing Research, Beijing Innovation Center for Future Chip, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047545398","display_name":"Lei Deng","orcid":"https://orcid.org/0000-0002-5172-9411"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Deng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015325570","display_name":"Bangyan Wang","orcid":"https://orcid.org/0000-0002-5240-7238"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bangyan Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018970859","display_name":"Guoqi Li","orcid":"https://orcid.org/0000-0002-8994-431X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqi Li","raw_affiliation_strings":["Department of Precision Instrument, Center for Brain Inspired Computing Research, Beijing Innovation Center for Future Chip, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Precision Instrument, Center for Brain Inspired Computing Research, Beijing Innovation Center for Future Chip, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037216840"],"corresponding_institution_ids":["https://openalex.org/I154570441","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.7661,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.86879987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"44","issue":"1","first_page":"13","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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":0.9994999766349792,"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/initialization","display_name":"Initialization","score":0.8194293975830078},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7470917701721191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6251869201660156},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.49793362617492676},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4572070240974426},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4114944338798523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33816957473754883},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32594555616378784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3090341091156006}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8194293975830078},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7470917701721191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251869201660156},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.49793362617492676},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4572070240974426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4114944338798523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33816957473754883},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32594555616378784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3090341091156006},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2020.3010201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3010201","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:32750821","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32750821","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2001.00254","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.00254","pdf_url":"https://arxiv.org/pdf/2001.00254","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":"pmh:oai:repository.hkust.edu.hk:1783.1-133009","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-133009","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.00254","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.00254","pdf_url":"https://arxiv.org/pdf/2001.00254","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G1003572525","display_name":null,"funder_award_id":"1730309","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7396753823","display_name":null,"funder_award_id":"1725447","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7549707144","display_name":null,"funder_award_id":"61876215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8116395671","display_name":null,"funder_award_id":"1817037","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"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W325680886","https://openalex.org/W1572306087","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1884490694","https://openalex.org/W1921523184","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2125930537","https://openalex.org/W2141473882","https://openalex.org/W2156387975","https://openalex.org/W2163605009","https://openalex.org/W2178237821","https://openalex.org/W2194775991","https://openalex.org/W2284050935","https://openalex.org/W2292729293","https://openalex.org/W2423689290","https://openalex.org/W2502312327","https://openalex.org/W2612252966","https://openalex.org/W2612445135","https://openalex.org/W2753358588","https://openalex.org/W2757196798","https://openalex.org/W2765407302","https://openalex.org/W2772798650","https://openalex.org/W2789027062","https://openalex.org/W2789210533","https://openalex.org/W2790621718","https://openalex.org/W2795783309","https://openalex.org/W2808465607","https://openalex.org/W2887597596","https://openalex.org/W2889560103","https://openalex.org/W2896801757","https://openalex.org/W2907121943","https://openalex.org/W2907747478","https://openalex.org/W2910114055","https://openalex.org/W2913830934","https://openalex.org/W2924828084","https://openalex.org/W2949117887","https://openalex.org/W2952258850","https://openalex.org/W2962804662","https://openalex.org/W2962894770","https://openalex.org/W2963446712","https://openalex.org/W2963454111","https://openalex.org/W2963570896","https://openalex.org/W2963685250","https://openalex.org/W2963918968","https://openalex.org/W2964065616","https://openalex.org/W2964081807","https://openalex.org/W2964088238","https://openalex.org/W2966173098","https://openalex.org/W2978031686","https://openalex.org/W2995941914","https://openalex.org/W3048030262","https://openalex.org/W3098011980","https://openalex.org/W3102633758","https://openalex.org/W4246193833","https://openalex.org/W4250482878","https://openalex.org/W4288621368","https://openalex.org/W4289494182","https://openalex.org/W4295151193","https://openalex.org/W4297775537","https://openalex.org/W4298392601","https://openalex.org/W4300537377","https://openalex.org/W6611137662","https://openalex.org/W6634093180","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6640185926","https://openalex.org/W6678818196","https://openalex.org/W6682889407","https://openalex.org/W6684191040","https://openalex.org/W6685315510","https://openalex.org/W6695676441","https://openalex.org/W6697265621","https://openalex.org/W6717556742","https://openalex.org/W6724804524","https://openalex.org/W6730172645","https://openalex.org/W6737664043","https://openalex.org/W6739879593","https://openalex.org/W6743969146","https://openalex.org/W6744331365","https://openalex.org/W6745136726","https://openalex.org/W6746375932","https://openalex.org/W6749180595","https://openalex.org/W6752356114","https://openalex.org/W6752969139","https://openalex.org/W6754615192","https://openalex.org/W6754819195","https://openalex.org/W6758094429","https://openalex.org/W6758417431","https://openalex.org/W6761071236","https://openalex.org/W6768555828"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W4226466875","https://openalex.org/W2977257638","https://openalex.org/W4288095186","https://openalex.org/W3210541621","https://openalex.org/W3016456819"],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"of":[3,38,49,59,72,120,178],"deep":[4],"neural":[5],"networks":[6,45],"(DNNs)":[7],"in":[8,67,91,123,247,252],"recent":[9],"years":[10],"can":[11],"be":[12],"attributed":[13],"to":[14,26,43,56,165,174,244],"the":[15,28,57,70,92,99,118,140,176],"various":[16],"techniques":[17,32],"that":[18,46,205],"address":[19],"gradient":[20,50,121],"explosion":[21,51],"and":[22,33,52,62,103,171,193,200,249,278,292,304],"vanishing.":[23,53],"In":[24,94],"order":[25],"understand":[27],"principle":[29],"behind":[30,214],"these":[31],"develop":[34],"new":[35,236],"methods,":[36],"plenty":[37],"metrics":[39,74],"have":[40],"been":[41],"proposed":[42],"identify":[44],"are":[47,187,294],"free":[48,157],"However,":[54],"due":[55],"diversity":[58,177],"network":[60,179,201],"components":[61],"complex":[63,79,167],"serial-parallel":[64,168],"hybrid":[65,169],"connections":[66,170],"modern":[68],"DNNs,":[69],"evaluation":[71,134],"existing":[73,220],"usually":[75],"requires":[76],"strong":[77],"assumptions,":[78],"statistical":[80,153],"analysis,":[81,225],"or":[82],"has":[83,266,279],"limited":[84],"application":[85],"fields,":[86],"which":[87,116,265],"constraints":[88],"their":[89],"spread":[90],"community.":[93],"this":[95],"paper,":[96],"inspired":[97],"by":[98,190,296],"Gradient":[100],"Norm":[101],"Equality":[102],"dynamical":[104,142],"isometry,":[105],"we":[106,148,195,217,255],"first":[107],"propose":[108,149,256],"a":[109,150,172,211,235,241,257],"novel":[110,258],"metric":[111,192],"called":[112],"Block":[113,128,207],"Dynamical":[114,129,208],"Isometry,":[115],"measures":[117],"change":[119],"norm":[122],"individual":[124],"blocks.":[125],"Because":[126],"our":[127,191,206,224,290],"Isometry":[130,209],"is":[131,210],"norm-based,":[132],"its":[133],"needs":[135],"weaker":[136],"assumptions":[137],"compared":[138],"with":[139],"original":[141],"isometry.":[143],"To":[144],"mitigate":[145],"challenging":[146],"derivation,":[147],"highly":[151],"modularized":[152],"framework":[154,160],"based":[155,222],"on":[156,223,299],"probability.":[158],"Our":[159],"includes":[161],"several":[162,182],"key":[163],"theorems":[164],"handle":[166],"library":[173],"cover":[175],"components.":[180],"Besides,":[181],"sufficient":[183],"conditions":[184],"for":[185,232,238],"prerequisites":[186],"provided.":[188],"Powered":[189],"framework,":[194],"analyze":[196],"extensive":[197,297],"initialization,":[198],"normalization,":[199,240,264],"structures.":[202],"We":[203],"find":[204],"universal":[212],"philosophy":[213],"them.":[215],"Then,":[216],"improve":[218],"some":[219],"methods":[221,293],"including":[226],"an":[227],"activation":[228],"function":[229],"selection":[230],"strategy":[231],"initialization":[233],"techniques,":[234],"configuration":[237],"weight":[239],"depth-aware":[242],"way":[243],"derive":[245],"coefficients":[246],"SeLU,":[248],"initialization/weight":[250],"normalization":[251,259,274],"DenseNet.":[253],"Moreover,":[254],"technique":[260],"named":[261],"second":[262],"moment":[263],"30":[267],"percent":[268],"fewer":[269],"computation":[270],"overhead":[271],"than":[272],"batch":[273,284],"without":[275],"accuracy":[276],"loss":[277],"better":[280],"performance":[281],"under":[282],"micro":[283],"size.":[285],"Last":[286],"but":[287],"not":[288],"least,":[289],"conclusions":[291],"evidenced":[295],"experiments":[298],"multiple":[300],"models":[301],"over":[302],"CIFAR-10":[303],"ImageNet.":[305]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}