{"id":"https://openalex.org/W2898737887","doi":null,"title":"How deep is deep enough? - Optimizing deep neural network architecture","display_name":"How deep is deep enough? - Optimizing deep neural network architecture","publication_year":2018,"publication_date":"2018-11-05","ids":{"openalex":"https://openalex.org/W2898737887","mag":"2898737887"},"language":"en","primary_location":{"id":"mag:2898737887","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1811.01753","pdf_url":null,"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,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1811.01753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026690582","display_name":"Achim Schilling","orcid":"https://orcid.org/0000-0001-9543-305X","observed_orcids":["https://orcid.org/0000-0001-9543-305X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Achim Schilling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016814029","display_name":"Jonas Rietsch","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonas Rietsch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049878919","display_name":"Richard Carl Gerum","orcid":"https://orcid.org/0000-0001-5893-2650","observed_orcids":["https://orcid.org/0000-0001-5893-2650"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Gerum","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5893-2650","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102712008","display_name":"Holger Schulze","orcid":"https://orcid.org/0000-0002-0449-4541","observed_orcids":["https://orcid.org/0000-0002-0449-4541"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Holger Schulze","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0449-4541","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009671657","display_name":"Claus Metzner","orcid":"https://orcid.org/0000-0002-5709-4306","observed_orcids":["https://orcid.org/0000-0002-5709-4306"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claus Metzner","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5709-4306","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062539159","display_name":"Patrick Krau\u00df","orcid":"https://orcid.org/0000-0002-6611-7733","observed_orcids":["https://orcid.org/0000-0002-6611-7733"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Krau\u00df","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6611-7733","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9711999893188477,"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":0.9711999893188477,"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":0.009499999694526196,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0066999997943639755,"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/deep-learning-architectures","display_name":"deep learning architectures","score":0.7680000066757202},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"deep belief network","score":0.7789999842643738},{"id":"https://openalex.org/keywords/unsupervised-pretraining","display_name":"unsupervised pre-training","score":0.7850000262260437},{"id":"https://openalex.org/keywords/mnist-classification","display_name":"MNIST classification","score":0.6489999890327454},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.609000027179718},{"id":"https://openalex.org/keywords/feature-detectors","display_name":"feature detectors","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7995871305465698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365033388137817},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6260183453559875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6242443323135376},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6239659786224365},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6161397099494934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.582789957523346},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5563948750495911},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49439167976379395},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.47072044014930725},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4576943516731262},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45402035117149353},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.44417932629585266},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4416866600513458},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32096803188323975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20455145835876465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2898737887","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1811.01753","pdf_url":null,"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,"listed_in":[],"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}],"best_oa_location":{"id":"mag:2898737887","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1811.01753","pdf_url":null,"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,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W113230244","https://openalex.org/W1522301498","https://openalex.org/W1592861455","https://openalex.org/W1686810756","https://openalex.org/W1973445088","https://openalex.org/W1993436046","https://openalex.org/W2064630666","https://openalex.org/W2064675550","https://openalex.org/W2072128103","https://openalex.org/W2100495367","https://openalex.org/W2108598243","https://openalex.org/W2110798204","https://openalex.org/W2112796928","https://openalex.org/W2113459411","https://openalex.org/W2116064496","https://openalex.org/W2116825644","https://openalex.org/W2145339207","https://openalex.org/W2146292423","https://openalex.org/W2157629899","https://openalex.org/W2165533158","https://openalex.org/W2166049352","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2295582178","https://openalex.org/W2304648132","https://openalex.org/W2531409750","https://openalex.org/W2726198599","https://openalex.org/W2736941579","https://openalex.org/W2750384547","https://openalex.org/W2766447205","https://openalex.org/W2799796340","https://openalex.org/W2903995489","https://openalex.org/W2964153729","https://openalex.org/W3105432754","https://openalex.org/W6911750326"],"related_works":["https://openalex.org/W3146058829","https://openalex.org/W2948082157","https://openalex.org/W3118518415","https://openalex.org/W7089834971","https://openalex.org/W2115781030","https://openalex.org/W4396782193","https://openalex.org/W2996788557","https://openalex.org/W2913012684","https://openalex.org/W2554646042","https://openalex.org/W4403999598"],"abstract_inverted_index":{"Deep":[0,126],"neural":[1,192],"networks":[2,193],"use":[3],"stacked":[4],"layers":[5,189],"of":[6,20,48,54,92,97,100,106,111,124,188,197],"feature":[7],"detectors":[8],"to":[9,81,88,183],"repeatedly":[10],"transform":[11],"the":[12,26,30,45,52,64,84,93,98,107,112,119,134,142,161,175,185],"input":[13,21,94,198],"data,":[14,95],"so":[15],"that":[16,129,141,174],"structurally":[17],"different":[18,73],"classes":[19,75],"become":[22],"well":[23,72,103],"separated":[24],"in":[25,37,50,77,121,190],"final":[27],"layer.":[28,79,116],"While":[29],"method":[31],"has":[32],"turned":[33],"out":[34],"extremely":[35],"powerful":[36],"many":[38],"applications,":[39],"its":[40,82],"success":[41],"depends":[42],"critically":[43],"on":[44,133],"correct":[46],"choice":[47],"hyperparameters,":[49],"particular":[51],"number":[53,99,108,187],"network":[55,149,163],"layers.":[56],"Here,":[57],"we":[58,139],"introduce":[59],"a":[60,115,125,180],"new":[61],"measure,":[62],"called":[63],"generalized":[65],"discrimination":[66],"value":[67],"(GDV),":[68],"which":[69],"quantifies":[70],"how":[71],"object":[74],"separate":[76],"each":[78,122,147],"Due":[80],"definition,":[83],"GDV":[85,120,143,176],"is":[86],"invariant":[87],"translation":[89],"and":[90,109],"scaling":[91],"independent":[96,105],"features,":[101],"as":[102,104,179],"permutation":[110],"neurons":[113],"within":[114],"We":[117],"compute":[118],"layer":[123,157],"Belief":[127],"Network":[128],"was":[130],"trained":[131],"unsupervised":[132],"MNIST":[135],"data":[136,167],"set.":[137],"Strikingly,":[138],"find":[140],"first":[144],"improves":[145],"with":[146],"successive":[148],"layer,":[150],"but":[151],"then":[152],"gets":[153],"worse":[154],"again":[155],"beyond":[156],"30,":[158],"thus":[159],"indicating":[160],"optimal":[162,186],"depth":[164],"for":[165,194],"this":[166],"classification":[168],"task.":[169],"Our":[170],"further":[171],"investigations":[172],"suggest":[173],"can":[177],"serve":[178],"universal":[181],"tool":[182],"determine":[184],"deep":[191],"any":[195],"type":[196],"data.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2018-11-09T00:00:00"}