{"id":"https://openalex.org/W1667249920","doi":"https://doi.org/10.1109/ijcnn.2015.7280459","title":"Improving deep neural networks using softplus units","display_name":"Improving deep neural networks using softplus units","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1667249920","doi":"https://doi.org/10.1109/ijcnn.2015.7280459","mag":"1667249920"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2015.7280459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2015.7280459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085132445","display_name":"Hao Zheng","orcid":"https://orcid.org/0000-0003-0829-9660"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084649692","display_name":"Zhanlei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanlei Yang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039635290","display_name":"Wenju Liu","orcid":"https://orcid.org/0000-0001-9088-8282"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenju Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111098694","display_name":"Jizhong Liang","orcid":"https://orcid.org/0009-0005-9244-8674"},"institutions":[{"id":"https://openalex.org/I1335486098","display_name":"Electric Power Research Institute","ror":"https://ror.org/02dqztz06","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1335486098"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jizhong Liang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","Electric Power Research Institute of ShanXi Electric Power Company, China State Grid Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Electric Power Research Institute of ShanXi Electric Power Company, China State Grid Corp, China","institution_ids":["https://openalex.org/I1335486098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074204778","display_name":"Yanpeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1335486098","display_name":"Electric Power Research Institute","ror":"https://ror.org/02dqztz06","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1335486098"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanpeng Li","raw_affiliation_strings":["Electric Power Research, China State Grid Corp","Electric Power Research Institute of ShanXi Electric Power Company, China State Grid Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electric Power Research, China State Grid Corp","institution_ids":[]},{"raw_affiliation_string":"Electric Power Research Institute of ShanXi Electric Power Company, China State Grid Corp, China","institution_ids":["https://openalex.org/I1335486098"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":235,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7891510128974915},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.7726187705993652},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.7611770629882812},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7527307271957397},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6095758676528931},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5831143260002136},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5599697232246399},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5336946249008179},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5227560997009277},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48779943585395813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45469748973846436},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42222729325294495},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.41517969965934753},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33312684297561646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3146536350250244},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06797322630882263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891510128974915},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.7726187705993652},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.7611770629882812},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7527307271957397},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6095758676528931},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5831143260002136},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5599697232246399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5336946249008179},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5227560997009277},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48779943585395813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45469748973846436},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42222729325294495},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.41517969965934753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33312684297561646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3146536350250244},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06797322630882263},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2015.7280459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2015.7280459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1665214252","https://openalex.org/W1904365287","https://openalex.org/W1993882792","https://openalex.org/W2004227461","https://openalex.org/W2029947361","https://openalex.org/W2061305730","https://openalex.org/W2100495367","https://openalex.org/W2107982609","https://openalex.org/W2289330286","https://openalex.org/W2359377300","https://openalex.org/W2394932179","https://openalex.org/W2400753342","https://openalex.org/W6604254268","https://openalex.org/W6637242042","https://openalex.org/W6640036494","https://openalex.org/W6696469593"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3047779762","https://openalex.org/W1520030019","https://openalex.org/W2071654592","https://openalex.org/W3104477175","https://openalex.org/W2088157920","https://openalex.org/W4313324256","https://openalex.org/W2019022049","https://openalex.org/W3082178636"],"abstract_inverted_index":{"Recently,":[0],"DNNs":[1,33,91,101,122,152,170],"have":[2,66,102],"achieved":[3],"great":[4],"improvement":[5,159],"for":[6,106,121,126],"acoustic":[7,124],"modeling":[8,125],"in":[9,87,94,123],"speech":[10],"recognition":[11,109,129],"tasks.":[12,130],"However,":[13,99],"it":[14],"is":[15,29],"difficult":[16],"to":[17,69,141,164,168],"train":[18],"the":[19,23,38,48,80,86,107,116,143,151,169],"models":[20],"well":[21],"when":[22,31],"depth":[24,49],"grows.":[25],"One":[26],"main":[27],"reason":[28],"that":[30],"training":[32,55],"with":[34,53,59,78,153,172],"traditional":[35],"sigmoid":[36,174],"units,":[37],"derivatives":[39],"damp":[40],"sharply":[41],"while":[42],"back-propagating":[43],"between":[44],"layers,":[45],"which":[46],"restrict":[47],"of":[50,85,118,145],"model":[51],"especially":[52],"insufficient":[54],"data.":[56],"To":[57],"deal":[58],"this":[60,112],"problem,":[61],"some":[62],"unbounded":[63],"activation":[64],"functions":[65],"been":[67,103],"proposed":[68],"preserve":[70],"sufficient":[71],"gradients,":[72],"including":[73],"ReLU":[74],"and":[75,82,97,135,160,176],"softplus.":[76],"Compared":[77],"ReLU,":[79],"smoothing":[81],"nonzero":[83],"properties":[84],"gradient":[88],"makes":[89],"softplus-based":[90,100],"perform":[92],"better":[93],"both":[95],"stabilization":[96],"performance.":[98],"rarely":[104],"exploited":[105],"phoneme":[108,128],"task.":[110],"In":[111],"paper,":[113],"we":[114],"explore":[115],"use":[117],"softplus":[119,146,154],"units":[120,155,175],"context-independent":[127],"The":[131],"revised":[132],"RBM":[133],"pre-training":[134],"dropout":[136],"strategy":[137],"are":[138],"also":[139],"applied":[140],"improve":[142],"performance":[144,158],"units.":[147],"Experiments":[148],"show":[149],"that,":[150],"get":[156,165],"significantly":[157],"uses":[161],"less":[162],"epochs":[163],"convergence":[166],"compared":[167],"trained":[171],"standard":[173],"ReLUs.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}