{"id":"https://openalex.org/W2985449552","doi":"https://doi.org/10.37727/jkdas.2019.21.5.2289","title":"Performance Comparison Among Deep Neural Networks Consisting of Various Constituents","display_name":"Performance Comparison Among Deep Neural Networks Consisting of Various Constituents","publication_year":2019,"publication_date":"2019-10-31","ids":{"openalex":"https://openalex.org/W2985449552","doi":"https://doi.org/10.37727/jkdas.2019.21.5.2289","mag":"2985449552"},"language":"en","primary_location":{"id":"doi:10.37727/jkdas.2019.21.5.2289","doi":"https://doi.org/10.37727/jkdas.2019.21.5.2289","is_oa":false,"landing_page_url":"https://doi.org/10.37727/jkdas.2019.21.5.2289","pdf_url":null,"source":{"id":"https://openalex.org/S2764654602","display_name":"The Korean Data Analysis Society","issn_l":"1229-2354","issn":["1229-2354","2733-9173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["kci-registered"],"host_organization":"https://openalex.org/P4323283706","host_organization_name":"Korean Data Analysis Society","host_organization_lineage":["https://openalex.org/P4323283706"],"host_organization_lineage_names":["Korean Data Analysis Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Korean Data Analysis Society","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5039700627","display_name":"Yu Seon Tak","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Seon Tak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110112763","display_name":"Hyeong Chul Jeong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyeong Chul Jeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111998160","display_name":"Jin Myung Jung","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Myung Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"5","first_page":"2289","last_page":"2301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7919999957084656,"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/T10320","display_name":"Neural Networks and Applications","score":0.7919999957084656,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.09839999675750732,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05270000174641609,"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/deep-neural-network","display_name":"deep neural network","score":0.9079999923706055},{"id":"https://openalex.org/keywords/hyperparameter-configuration","display_name":"hyperparameter configuration","score":0.6639999747276306},{"id":"https://openalex.org/keywords/optimization-algorithm-comparison","display_name":"optimizer comparison","score":0.7049999833106995},{"id":"https://openalex.org/keywords/adam-optimizer","display_name":"Adam optimizer","score":0.8550000190734863},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"gradient descent","score":0.9190000295639038},{"id":"https://openalex.org/keywords/activation-functions","display_name":"activation functions","score":0.8939999938011169},{"id":"https://openalex.org/keywords/relu","display_name":"ReLU","score":0.9070000052452087},{"id":"https://openalex.org/keywords/sigmoid","display_name":"sigmoid","score":0.9649999737739563},{"id":"https://openalex.org/keywords/dropout","display_name":"dropout","score":0.9509999752044678},{"id":"https://openalex.org/keywords/regularization","display_name":"regularization","score":0.9129999876022339},{"id":"https://openalex.org/keywords/tikhonov-regularization","display_name":"Tikhonov regularization","score":0.8230000138282776},{"id":"https://openalex.org/keywords/weight-initialization","display_name":"weight initialization","score":0.878000020980835},{"id":"https://openalex.org/keywords/he-initialization","display_name":"He initialization","score":0.984000027179718},{"id":"https://openalex.org/keywords/model-performance-comparison","display_name":"model performance comparison","score":0.6480000019073486},{"id":"https://openalex.org/keywords/food-ingredients","display_name":"food ingredients","score":0.40700000524520874},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.48100000619888306},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.9649999737739563},{"id":"https://openalex.org/keywords/image-recognition","display_name":"image recognition","score":0.3160000145435333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6179999709129333},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.4390000104904175},{"id":"https://openalex.org/keywords/computer-vision","display_name":"computer vision","score":0.38100001215934753},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5894601941108704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46408459544181824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36497581005096436},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35682612657546997},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.35201534628868103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3223382830619812}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.37727/jkdas.2019.21.5.2289","doi":"https://doi.org/10.37727/jkdas.2019.21.5.2289","is_oa":false,"landing_page_url":"https://doi.org/10.37727/jkdas.2019.21.5.2289","pdf_url":null,"source":{"id":"https://openalex.org/S2764654602","display_name":"The Korean Data Analysis Society","issn_l":"1229-2354","issn":["1229-2354","2733-9173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["kci-registered"],"host_organization":"https://openalex.org/P4323283706","host_organization_name":"Korean Data Analysis Society","host_organization_lineage":["https://openalex.org/P4323283706"],"host_organization_lineage_names":["Korean Data Analysis Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Korean Data Analysis Society","raw_type":"journal-article"},{"id":"mag:3177755874","doi":null,"is_oa":false,"landing_page_url":"http://dspace.kci.go.kr/handle/kci/1444536?show=full","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3177755874","https://openalex.org/W2978543776","https://openalex.org/W2752066676","https://openalex.org/W4210647952","https://openalex.org/W7035156497","https://openalex.org/W3090701121","https://openalex.org/W2801154828","https://openalex.org/W3130022237","https://openalex.org/W7214981001","https://openalex.org/W3006263399"],"abstract_inverted_index":{"\uba38\uc2e0\ub7ec\ub2dd":[0],"\ubaa8\ub378":[1],"\uc911\uc5d0":[2],"\ud558\ub098\uc778":[3],"\ub525\ub274\ub7f4\ub137":[4,19,35,59,156],"\ubaa8\ub378\uc740":[5,20],"\ucd5c\uadfc":[6],"\uc6d4\ub4f1\ud55c":[7],"\uc131\ub2a5\uc744":[8,114],"\ubcf4\uc774\uba70,":[9],"\uc790\uc728\uc8fc\ud589,":[10],"\uc790\uc5f0\uc5b4":[11],"\ucc98\ub9ac":[12],"\ub4f1":[13],"\ub2e4\uc591\ud55c":[14],"\ubd84\uc57c\uc5d0\uc11c":[15],"\ub9ce\uc774":[16],"\uc5f0\uad6c\ub418\uace0":[17],"\uc788\ub2e4.":[18],"\uadf8":[21,29],"\uad6c\uc131\uc694\uc18c\uac00":[22],"\ub2e4\uc591\ud558\uae30":[23],"\ub54c\ubb38\uc5d0,":[24],"\ubaa8\ub378\uc744":[25,60,157],"\uc5b4\ub5bb\uac8c":[26],"\uad6c\uc131\ud558\ub294\uc9c0\uc5d0":[27],"\ub530\ub77c\uc11c":[28],"\uc131\ub2a5\uc774":[30,129,146],"\ud06c\uac8c":[31],"\ub2ec\ub77c\uc9c4\ub2e4.":[32],"\ubcf8":[33],"\uc5f0\uad6c\uc5d0\uc11c\ub294":[34],"\ubaa8\ub378\uc758":[36],"\uad6c\uc131":[37],"\uc694\uc18c":[38,112],"5":[39,53],"\uac00\uc9c0":[40,54],"-":[41,50],"\uac00\uc911\uce58":[42,48,100],"\ucd5c\uc801\ud654,":[43],"\ud65c\uc131\ud654":[44,92,134,137],"\ud568\uc218,":[45,93],"\ub4dc\ub86d\uc544\uc6c3,":[46],"\uc815\uaddc\ud654,":[47],"\ucd08\uae30\ud654":[49],"\ub97c":[51],"\uc815\ud558\uace0,":[52],"\uad6c\uc131\uc694\uc18c\uc758":[55],"\uac00\ub2a5\ud55c":[56],"\uc870\ud569":[57],"48\uac00\uc9c0\uc758":[58],"\ub9cc\ub4e4\uc5c8\ub2e4.":[61],"\ub9cc\ub4e0":[62],"\ubaa8\ub378\ub4e4\uc758":[63],"\uc131\ub2a5":[64,154],"\ud3c9\uac00\ub97c":[65],"\uc704\ud574\uc11c,":[66],"\uc74c\uc2dd\uc758":[67],"\uc131\ubd84\ub4e4\uc744":[68],"\uac00\uc9c0\uace0":[69],"20\uac1c\uc758":[70],"\ub098\ub77c":[71],"\uc911":[72],"\ud558\ub098\ub97c":[73],"\uc608\uce21\ud558\ub294":[74],"Kaggle\uc758":[75],"what":[76],"s":[77],"cooking":[78,224],"\ub370\uc774\ud130\ub97c":[79],"\ud65c\uc6a9\ud558\uc600\ub2e4.":[80],"\uacb0\uacfc\uc801\uc73c\ub85c,":[81],"\uc801\uc751\ubaa8\uba58\ud2b8\ucd94\uc815(adaptive":[82],"moment":[83],"estimation,":[84],"Adam)":[85],"\ucd5c\uc801\ud654":[86,118,122],"\uae30\ubc95,":[87],"\uc815\ub958\uc120\ud615\ub2e8\uc704(rectified":[88],"linear":[89],"unit,":[90],"ReLU)":[91],"\ub9bf\uc9c0(ridge)":[94],"\uc815\uaddc\ud654":[95],"\ubbf8\uc0ac\uc6a9,":[96],"\ub4dc\ub86d\uc544\uc6c3":[97],"\uc0ac\uc6a9,":[98],"He":[99,261],"\ucd08\uae30\ud654\ub77c\ub294":[101],"\uad6c\uc131\uc73c\ub85c":[102],"\ub525\ub274\ub7f4\ub137\uc744":[103],"\uad6c\uc131\ud588\uc744":[104],"\ub54c":[105],"\uac00\uc7a5":[106],"\uc88b\uc740":[107,130,147,155],"\uc131\ub2a5(\uc815\ud655\ub3c4:":[108],"79.45%)\uc744":[109],"\ubcf4\uc600\ub2e4.":[110],"\uac01":[111],"\ubcc4\ub85c":[113],"\ube44\uad50\ud558\uc600\uc744":[115],"\ub54c\uc5d0\ub294,":[116],"Adam":[117,256,290],"\uae30\ubc95\uc774":[119],"\uacbd\uc0ac\ud558\uac15(gradient":[120],"descent)":[121],"\uae30\ubc95\uc744":[123],"\uc0ac\uc6a9\ud55c":[124,139],"\ubaa8\ub378\ub4e4":[125,140],"\ubcf4\ub2e4":[126,141],"\ud3c9\uade0\uc801\uc73c\ub85c":[127,142],"56%\uc815\ub3c4\uc758":[128],"\uac83\uc73c\ub85c":[131,148],"\ub098\ud0c0\ub0ac\uace0,":[132],"ReLU":[133,258,307],"\ud568\uc218\uac00":[135],"\uc2dc\uadf8\ubaa8\uc774\ub4dc(sigmoid)":[136],"\ud568\uc218\ub97c":[138],"\uc57d":[143],"3%":[144,312],"\uc815\ub3c4":[145],"\ub098\ud0c0\ub0ac\ub2e4.":[149],"\uc774":[150],"\uc5f0\uad6c\uc758":[151],"\uacb0\uacfc\uac00":[152],"\ub354":[153],"\ub9cc\ub4dc\ub294\ub370":[158],"\uae30\uc5ec\ud560":[159],"\uc218":[160],"\uc788\uae30\ub97c":[161],"\uae30\ub300\ud55c\ub2e4.In":[162],"these":[163],"days,":[164],"deep":[165],"neural":[166],"networks":[167],"(DNN)":[168],"yield":[169],"the":[170,181,198,211,242,249,252,274,281,304,324],"most":[171],"remarkable":[172],"performance":[173,182,199,276,334],"among":[174,248],"machine-learning":[175],"algorithms.":[176],"Many":[177],"researchers":[178],"claim":[179],"that":[180,203,228,323],"of":[183,200,205,231,255,265,270,326],"DNN":[184,253,335],"might":[185],"be":[186],"different":[187],"according":[188],"to":[189,210,238,331],"its":[190,234],"constituents.":[191],"In":[192],"this":[193,327],"paper,":[194],"we":[195],"thoroughly":[196],"analyze":[197],"48":[201,243,250],"DNNs":[202,288,305],"consist":[204],"various":[206],"constituents":[207],"in":[208,226,279],"regard":[209],"five":[212],"factors,":[213],"i.e.":[214],"optimizer,":[215,257,302],"activation":[216,259,308,319],"function,":[217,260],"dropout,":[218,266],"regularization":[219,272],"and":[220,233,240,267,303],"weight":[221,262],"initialization.":[222],"What\u2019s":[223],"data":[225],"Kaggle":[227],"contains":[229],"ingredients":[230],"food":[232,285],"nation":[235,282],"are":[236],"employed":[237],"train":[239],"test":[241],"models.":[244,336],"As":[245],"a":[246],"result,":[247],"DNNs,":[251],"composed":[254],"initialization,":[263],"use":[264,269],"no":[268],"ridge":[271],"produce":[273],"best":[275],"(accuracy:":[277],"79.45%)":[278],"predicting":[280],"based":[283],"on":[284],"ingredients.":[286],"The":[287],"using":[289,299,306,317],"optimizer":[291],"averagely":[292,310],"show":[293,311],"56%":[294],"higher":[295,313],"accuracy":[296,314],"than":[297,315],"those":[298,316],"gradient":[300],"descent":[301],"function":[309],"sigmoid":[318],"function.":[320],"We":[321],"expect":[322],"result":[325],"study":[328],"can":[329],"assist":[330],"construct":[332],"better":[333]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-11-22T00:00:00"}