{"id":"https://openalex.org/W2949491641","doi":"https://doi.org/10.3390/e21070627","title":"Smooth Function Approximation by Deep Neural Networks with General Activation Functions","display_name":"Smooth Function Approximation by Deep Neural Networks with General Activation Functions","publication_year":2019,"publication_date":"2019-06-26","ids":{"openalex":"https://openalex.org/W2949491641","doi":"https://doi.org/10.3390/e21070627","mag":"2949491641","pmid":"https://pubmed.ncbi.nlm.nih.gov/33267341"},"language":"en","primary_location":{"id":"doi:10.3390/e21070627","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e21070627","pdf_url":null,"source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/e21070627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ilsang Ohn","orcid":"https://orcid.org/0000-0003-3953-5953"},"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":"Ilsang Ohn","raw_affiliation_strings":["Department of Statistics, Seoul National University, Seoul 08826, Korea"],"raw_orcid":"https://orcid.org/0000-0003-3953-5953","affiliations":[{"raw_affiliation_string":"Department of Statistics, Seoul National University, Seoul 08826, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yongdai Kim","orcid":null},"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":"Yongdai Kim","raw_affiliation_strings":["Department of Statistics, Seoul National University, Seoul 08826, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Seoul National University, Seoul 08826, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2227},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2227},"fwci":4.3682,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95253081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"21","issue":"7","first_page":"627","last_page":"627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.41280001401901245,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.41280001401901245,"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":0.19040000438690186,"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/T12676","display_name":"Machine Learning and ELM","score":0.07360000163316727,"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/activation-function","display_name":"Activation function","score":0.864799976348877},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.755299985408783},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.5910999774932861},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.567300021648407},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.550000011920929},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5192000269889832},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47350001335144043}],"concepts":[{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.864799976348877},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.755299985408783},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5192000269889832},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4927999973297119},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47350001335144043},{"id":"https://openalex.org/C117148685","wikidata":"https://www.wikidata.org/wiki/Q6865376","display_name":"Minimax approximation algorithm","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40959998965263367},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C202286095","wikidata":"https://www.wikidata.org/wiki/Q579262","display_name":"Error function","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C98458673","wikidata":"https://www.wikidata.org/wiki/Q917657","display_name":"Step function","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C86582703","wikidata":"https://www.wikidata.org/wiki/Q7617824","display_name":"Stochastic neural network","level":4,"score":0.2614000141620636},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3390/e21070627","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e21070627","pdf_url":null,"source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:33267341","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33267341","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":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:arXiv.org:1906.06903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.06903","pdf_url":"https://arxiv.org/pdf/1906.06903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:pubmedcentral.nih.gov:7515121","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7515121","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:b679be97d72f46f9a1a7bf79a638b155","is_oa":true,"landing_page_url":"https://doaj.org/article/b679be97d72f46f9a1a7bf79a638b155","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 21, Iss 7, p 627 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/21/7/627/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e21070627","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e21070627","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e21070627","pdf_url":null,"source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1645616060","display_name":null,"funder_award_id":"SSTF-BA1601-02","funder_id":"https://openalex.org/F4320332195","funder_display_name":"Samsung"}],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1971735090","https://openalex.org/W1983776716","https://openalex.org/W2006240266","https://openalex.org/W2022465039","https://openalex.org/W2043919728","https://openalex.org/W2049393399","https://openalex.org/W2103496339","https://openalex.org/W2137983211","https://openalex.org/W2323427369","https://openalex.org/W2528305538","https://openalex.org/W2614181593","https://openalex.org/W2785811489","https://openalex.org/W2790159265","https://openalex.org/W2896005801","https://openalex.org/W2919115771","https://openalex.org/W2920824121","https://openalex.org/W2946302218","https://openalex.org/W2963146412","https://openalex.org/W3125537303","https://openalex.org/W6682889407","https://openalex.org/W6739285390"],"related_works":[],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"a":[3,46,73,84],"growing":[4],"interest":[5],"in":[6,117],"expressivity":[7],"of":[8,14,41,49,54,59,72,92,106],"deep":[9,42,74,108],"neural":[10,43,75,109],"networks.":[11],"However,":[12],"most":[13,58],"the":[15,24,38,66,89,103,107,113],"existing":[16],"work":[17],"about":[18],"this":[19,34],"topic":[20],"focuses":[21],"only":[22],"on":[23,96],"specific":[25],"activation":[26,50,55,62,93,115],"function":[27,82],"such":[28],"as":[29],"ReLU":[30],"or":[31],"sigmoid.":[32],"In":[33],"paper,":[35],"we":[36,101],"investigate":[37],"approximation":[39,86,98],"ability":[40],"networks":[44],"with":[45,112],"broad":[47],"class":[48,53,91],"functions.":[51,63,94],"This":[52],"functions":[56,116],"includes":[57],"frequently":[60],"used":[61],"We":[64],"derive":[65,102],"required":[67],"depth,":[68],"width":[69],"and":[70,120],"sparsity":[71],"network":[76,110],"to":[77],"approximate":[78],"any":[79],"H\u00f6lder":[80],"smooth":[81],"upto":[83],"given":[85],"error":[87,99],"for":[88],"large":[90],"Based":[95],"our":[97],"analysis,":[100],"minimax":[104],"optimality":[105],"estimators":[111],"general":[114],"both":[118],"regression":[119],"classification":[121],"problems.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2019-06-27T00:00:00"}