{"id":"https://openalex.org/W2909741332","doi":"https://doi.org/10.1162/neco_a_01235","title":"On the Effect of the Activation Function on the Distribution of Hidden Nodes in a Deep Network","display_name":"On the Effect of the Activation Function on the Distribution of Hidden Nodes in a Deep Network","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2909741332","doi":"https://doi.org/10.1162/neco_a_01235","mag":"2909741332","pmid":"https://pubmed.ncbi.nlm.nih.gov/31614106"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01235","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01235","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/neco_a_01235","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/neco_a_01235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084487318","display_name":"Philip M. Long","orcid":"https://orcid.org/0000-0002-1010-6197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Philip M. Long","raw_affiliation_strings":["Google Brain, Mountain View, CA 94043, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA 94043, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045805879","display_name":"Hanie Sedghi","orcid":"https://orcid.org/0000-0002-7163-5009"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanie Sedghi","raw_affiliation_strings":["Google Brain, Mountain View, CA 94043, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA 94043, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084487318"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.00894788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"31","issue":"12","first_page":"2562","last_page":"2580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9980000257492065,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9980000257492065,"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":0.9966999888420105,"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":0.9947999715805054,"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/function","display_name":"Function (biology)","score":0.621307373046875},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5994675159454346},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5767999291419983},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5465691685676575},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.5207762122154236},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5179089903831482},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5095548629760742},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.4708889126777649},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.46050378680229187},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44387325644493103},{"id":"https://openalex.org/keywords/probability-mass-function","display_name":"Probability mass function","score":0.42098382115364075},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3996901512145996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3147815763950348},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21894991397857666},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.15099066495895386},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13166624307632446}],"concepts":[{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.621307373046875},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5994675159454346},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5767999291419983},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5465691685676575},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.5207762122154236},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5179089903831482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5095548629760742},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.4708889126777649},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.46050378680229187},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44387325644493103},{"id":"https://openalex.org/C197096303","wikidata":"https://www.wikidata.org/wiki/Q869887","display_name":"Probability mass function","level":3,"score":0.42098382115364075},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3996901512145996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3147815763950348},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21894991397857666},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.15099066495895386},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13166624307632446},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/neco_a_01235","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01235","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/neco_a_01235","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:31614106","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31614106","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":"Neural computation","raw_type":null},{"id":"pmh:oai:arXiv.org:1901.02104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.02104","pdf_url":"https://arxiv.org/pdf/1901.02104","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:2909741332","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1901.02104.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.1901.02104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.02104","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":"doi:10.1162/neco_a_01235","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01235","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/neco_a_01235","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.44999998807907104,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1565715268","https://openalex.org/W1567512734","https://openalex.org/W1677182931","https://openalex.org/W2014280542","https://openalex.org/W2751862591","https://openalex.org/W2789210533","https://openalex.org/W2803268044","https://openalex.org/W2914484425","https://openalex.org/W2962804662","https://openalex.org/W2962939986","https://openalex.org/W2963063862","https://openalex.org/W2963570896","https://openalex.org/W2963679562","https://openalex.org/W2964052793","https://openalex.org/W2964065616","https://openalex.org/W2964088238","https://openalex.org/W3099517667","https://openalex.org/W4238404964","https://openalex.org/W4300234074"],"related_works":["https://openalex.org/W98638142","https://openalex.org/W2989472764","https://openalex.org/W3041499691","https://openalex.org/W2781204213","https://openalex.org/W3078407515","https://openalex.org/W2075407161","https://openalex.org/W2993488056","https://openalex.org/W2913010492","https://openalex.org/W3037508544","https://openalex.org/W2925259031","https://openalex.org/W2097216511","https://openalex.org/W3088153346","https://openalex.org/W3134110549","https://openalex.org/W2950657039","https://openalex.org/W2142486118","https://openalex.org/W67752311","https://openalex.org/W2610740309","https://openalex.org/W2951552039","https://openalex.org/W2997275225","https://openalex.org/W2338697629"],"abstract_inverted_index":{"We":[0,36,107,123],"analyze":[1],"the":[2,7,10,25,40,67,70,74,92,95,101,132,139,151],"joint":[3],"probability":[4,79],"distribution":[5],"on":[6,138],"lengths":[8],"of":[9,12,18,50,69,91,94,134],"vectors":[11],"hidden":[13,144],"variables":[14,145],"in":[15,63,78],"different":[16],"layers":[17],"a":[19,47,81,88,147],"fully":[20],"connected":[21],"deep":[22],"network,":[23],"when":[24],"weights":[26,97],"and":[27,98,100],"biases":[28,99],"are":[29,61],"chosen":[30],"randomly":[31],"according":[32],"to":[33,80,126,130],"gaussian":[34],"distributions.":[35],"show":[37,109,124],"that":[38,57,60,84,110,119,143],"if":[39],"activation":[41,55,102,140],"function":[42,90,103],"[Formula:":[43,104,116],"see":[44,105,117],"text]":[45,118],"satisfies":[46],"minimal":[48],"set":[49],"assumptions,":[51],"satisfied":[52],"by":[53],"all":[54],"functions":[56],"we":[58],"know":[59],"used":[62],"practice,":[64],"then,":[65],"as":[66,87],"width":[68],"network":[71],"gets":[72],"large,":[73],"\u201clength":[75],"process\u201d":[76],"converges":[77],"length":[82],"map":[83],"is":[85],"determined":[86],"simple":[89],"variances":[93],"random":[96],"text].":[106],"also":[108],"this":[111,128],"convergence":[112],"may":[113],"fail":[114],"for":[115],"violate":[120],"our":[121],"assumptions.":[122],"how":[125],"use":[127],"analysis":[129],"choose":[131],"variance":[133],"weight":[135],"initialization,":[136],"depending":[137],"function,":[141],"so":[142],"maintain":[146],"consistent":[148],"scale":[149],"throughout":[150],"network.":[152]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}