{"id":"https://openalex.org/W2963258470","doi":"https://doi.org/10.1109/iwcmc.2019.8766500","title":"A Vibrating Mechanism to Prevent Neural Networks from Overfitting","display_name":"A Vibrating Mechanism to Prevent Neural Networks from Overfitting","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2963258470","doi":"https://doi.org/10.1109/iwcmc.2019.8766500","mag":"2963258470"},"language":"en","primary_location":{"id":"doi:10.1109/iwcmc.2019.8766500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc.2019.8766500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC)","raw_type":"proceedings-article"},"type":"article","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/A5115597493","display_name":"Jian Xiong","orcid":null},"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":"Jian Xiong","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702866","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0002-1188-2120"},"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":"Kai Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396885","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-2928-2692"},"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":"Hao Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8921,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92926988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1737","last_page":"1742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"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":0.996999979019165,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9965999722480774,"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/overfitting","display_name":"Overfitting","score":0.7463955879211426},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6492344737052917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5491516590118408},{"id":"https://openalex.org/keywords/bernoulli-distribution","display_name":"Bernoulli distribution","score":0.5449376106262207},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5446559190750122},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.5348201394081116},{"id":"https://openalex.org/keywords/hyperplane","display_name":"Hyperplane","score":0.5021023750305176},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.48501917719841003},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.48337405920028687},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.444196492433548},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43526333570480347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4303252696990967},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.42474448680877686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4046025574207306},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37519192695617676},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35084742307662964},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22454479336738586},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16717484593391418},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.123758465051651},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1227295994758606},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.10466670989990234}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7463955879211426},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6492344737052917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5491516590118408},{"id":"https://openalex.org/C27956954","wikidata":"https://www.wikidata.org/wiki/Q391371","display_name":"Bernoulli distribution","level":3,"score":0.5449376106262207},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5446559190750122},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.5348201394081116},{"id":"https://openalex.org/C68693459","wikidata":"https://www.wikidata.org/wiki/Q657586","display_name":"Hyperplane","level":2,"score":0.5021023750305176},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.48501917719841003},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.48337405920028687},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.444196492433548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43526333570480347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4303252696990967},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.42474448680877686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4046025574207306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37519192695617676},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35084742307662964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22454479336738586},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16717484593391418},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.123758465051651},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1227295994758606},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.10466670989990234},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcmc.2019.8766500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc.2019.8766500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1504194272","https://openalex.org/W1793121960","https://openalex.org/W2004915807","https://openalex.org/W2088978850","https://openalex.org/W2095705004","https://openalex.org/W2120615054","https://openalex.org/W2158899491","https://openalex.org/W2170240176","https://openalex.org/W2252335727","https://openalex.org/W2301541953","https://openalex.org/W2413904250","https://openalex.org/W2468328197","https://openalex.org/W2470673105","https://openalex.org/W2593887162","https://openalex.org/W2622365670","https://openalex.org/W2741271950","https://openalex.org/W2808133401","https://openalex.org/W2951008357","https://openalex.org/W2952230511","https://openalex.org/W2963012544","https://openalex.org/W2963446712","https://openalex.org/W2963626623","https://openalex.org/W4294238563","https://openalex.org/W6600213771","https://openalex.org/W6638318767","https://openalex.org/W6674330103","https://openalex.org/W6683738474","https://openalex.org/W6685053522","https://openalex.org/W6715835459","https://openalex.org/W6719819555","https://openalex.org/W6734429903"],"related_works":["https://openalex.org/W4298017035","https://openalex.org/W3110700750","https://openalex.org/W2792147139","https://openalex.org/W4226354336","https://openalex.org/W2998675825","https://openalex.org/W3128220493","https://openalex.org/W2736804899","https://openalex.org/W2897443685","https://openalex.org/W4307654087","https://openalex.org/W2951100320"],"abstract_inverted_index":{"In":[0,30],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,13,21,37,53,92,121],"Vibrating":[6,46,113,136,156],"Mechanism,":[7,47],"which":[8,149],"can":[9,19,138],"be":[10],"understood":[11],"as":[12],"continuous":[14],"version":[15],"of":[16,62,77,84,105,110,154],"Dropout":[17],"and":[18,73],"achieve":[20,139],"certain":[22],"L1":[23,145],"regularization":[24,146],"effect":[25],"at":[26],"the":[27,32,44,48,63,66,70,74,78,81,85,96,103,111,135,151,155],"same":[28],"time.":[29],"Dropout,":[31,148],"parameters":[33,49],"are":[34,50],"discarded":[35],"with":[36],"probability":[38],"obeying":[39],"Bernoulli":[40],"distribution.":[41,59],"While":[42],"in":[43],"proposed":[45,112],"sampled":[51],"from":[52,102],"truncated":[54],"Gaussian":[55],"distribution":[56,64,79],"or":[57,147],"uniform":[58],"The":[60,108,131],"mean":[61],"is":[65,80,99,115],"result":[67,89,132],"trained":[68],"by":[69,91,117],"previous":[71,86],"iteration,":[72],"standard":[75],"deviation":[76],"absolute":[82],"value":[83],"iteration":[87],"training":[88],"multiplied":[90],"proportional":[93],"coefficient.":[94],"Besides,":[95],"performance":[97,152],"improvement":[98,153],"theoretically":[100],"analyzed":[101],"perspective":[104],"hyperplane":[106],"segmentation.":[107],"effectiveness":[109],"Mechanism":[114,137],"demonstrated":[116],"applying":[118],"it":[119],"for":[120,129],"text":[122],"classification":[123,141],"task.":[124],"We":[125],"choose":[126],"AG":[127],"dataset":[128],"test.":[130],"shows":[133],"that":[134],"better":[140],"accuracy":[142],"without":[143],"using":[144],"verifies":[150],"Mechanism.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}