{"id":"https://openalex.org/W2735608293","doi":"https://doi.org/10.1109/ijcnn.2017.7965900","title":"The effects of output codes on transfer learning in a deep convolutional neural net","display_name":"The effects of output codes on transfer learning in a deep convolutional neural net","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2735608293","doi":"https://doi.org/10.1109/ijcnn.2017.7965900","mag":"2735608293"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7965900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","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/A5031653834","display_name":"Steven Gutstein","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven Gutstein","raw_affiliation_strings":["United States Army Research Lab, MD"],"affiliations":[{"raw_affiliation_string":"United States Army Research Lab, MD","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013003113","display_name":"Ethan Stump","orcid":"https://orcid.org/0000-0002-0119-2169"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan Stump","raw_affiliation_strings":["United States Army Research Lab, MD"],"affiliations":[{"raw_affiliation_string":"United States Army Research Lab, MD","institution_ids":["https://openalex.org/I166416128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031653834"],"corresponding_institution_ids":["https://openalex.org/I166416128"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08381351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"350","issue":null,"first_page":"542","last_page":"548"},"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":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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":0.9976000189781189,"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/encoding","display_name":"Encoding (memory)","score":0.7340247631072998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6849665641784668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5932627320289612},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5576528906822205},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.5535135269165039},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5488206148147583},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5453044176101685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4452741742134094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4362788796424866},{"id":"https://openalex.org/keywords/overtraining","display_name":"Overtraining","score":0.41874101758003235},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4128567576408386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17634445428848267}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7340247631072998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6849665641784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5932627320289612},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5576528906822205},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.5535135269165039},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5488206148147583},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5453044176101685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4452741742134094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4362788796424866},{"id":"https://openalex.org/C2778534509","wikidata":"https://www.wikidata.org/wiki/Q334310","display_name":"Overtraining","level":3,"score":0.41874101758003235},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4128567576408386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17634445428848267},{"id":"https://openalex.org/C1862650","wikidata":"https://www.wikidata.org/wiki/Q186005","display_name":"Physical therapy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2781054738","wikidata":"https://www.wikidata.org/wiki/Q4813730","display_name":"Athletes","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7965900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W27961112","https://openalex.org/W1531648066","https://openalex.org/W1649754194","https://openalex.org/W1953590900","https://openalex.org/W2102933889","https://openalex.org/W2115733720","https://openalex.org/W2124033848","https://openalex.org/W2138621090","https://openalex.org/W2144656844","https://openalex.org/W2150295085","https://openalex.org/W2157364932","https://openalex.org/W2165698076","https://openalex.org/W2168939893","https://openalex.org/W2171590421","https://openalex.org/W2194321275","https://openalex.org/W2207555655","https://openalex.org/W2211041058","https://openalex.org/W2293597654","https://openalex.org/W2395579298","https://openalex.org/W2913340405","https://openalex.org/W2913932916","https://openalex.org/W2914484425","https://openalex.org/W3091905774","https://openalex.org/W3118608800","https://openalex.org/W3143107425","https://openalex.org/W4255932728","https://openalex.org/W4255949318","https://openalex.org/W6601146891","https://openalex.org/W6631884152","https://openalex.org/W6640737575","https://openalex.org/W6678360021","https://openalex.org/W6681389334","https://openalex.org/W6682222085","https://openalex.org/W6684956099","https://openalex.org/W6697214482"],"related_works":["https://openalex.org/W2130825577","https://openalex.org/W2093836487","https://openalex.org/W2065110043","https://openalex.org/W2186435175","https://openalex.org/W205267674","https://openalex.org/W2339864240","https://openalex.org/W2947435317","https://openalex.org/W641331424","https://openalex.org/W3047221865","https://openalex.org/W2345895352"],"abstract_inverted_index":{"The":[0,42],"output":[1,50,54,128],"encodings":[2,57,101,129,148,158,200],"of":[3,9,92,108,119,167,176,229],"neural":[4,29,153,257],"nets":[5,30],"determine":[6],"the":[7,10,84,106,165,186,197,207,213,224,227,230,245],"structure":[8],"space":[11],"in":[12,105,194],"which":[13,71,209],"inference":[14],"occurs.":[15],"Yet,":[16],"they":[17],"are":[18,47,126,149,210],"generally":[19,249],"given":[20],"very":[21],"little":[22],"thought.":[23],"It":[24],"is":[25,242],"common":[26],"practice":[27],"for":[28,68,102,133,159,174],"to":[31,37,45,65,70,155,180,204,220,244,251],"use":[32],"1-Hot":[33],"encoding":[34,114],"when":[35,254],"training":[36,184,218,255],"discriminate":[38],"among":[39,206,223],"many":[40],"classes.":[41,161],"primary":[43],"exceptions":[44],"this":[46,139],"error":[48],"correcting":[49],"codes,":[51],"and":[52,122],"semantic":[53,60,86,110],"encodings.":[55],"Output":[56],"based":[58],"upon":[59],"descriptors":[61],"cause":[62],"a":[63,90,97,109,152,177,238,256],"net":[64,98,154],"learn":[66,100,157],"responses":[67],"classes":[69,79,104,188,208],"it":[72],"has":[73],"not":[74],"been":[75],"exposed,":[76],"provided":[77],"those":[78],"may":[80],"be":[81,202],"characterized":[82],"by":[83],"same":[85],"descriptors.":[87],"This":[88,240],"raises":[89],"number":[91],"questions,":[93],"such":[94],"as":[95,183,217],"\u201cCan":[96],"implicitly":[99,156,198],"unobserved":[103,160,211],"absence":[107],"encoding,":[111],"or":[112,236],"any":[113],"that":[115,247],"requires":[116],"some":[117,127],"form":[118],"prior":[120],"knowledge":[121],"hand":[123],"crafting?\u201d.":[124],"Also,":[125,162],"better":[130],"than":[131],"others":[132],"learning":[134],"these":[135,168],"implicit":[136,169,231],"encodings?":[137],"In":[138],"paper,":[140],"we":[141,171,190],"will":[142,172],"compare":[143],"how":[144,195],"effectively":[145],"different":[146],"non-semantic":[147],"at":[150],"causing":[151],"while":[163],"evaluating":[164],"efficacy":[166,228],"encodings,":[170],"look":[173],"evidence":[175],"phenomenon":[178],"akin":[179,243],"over-training.":[181],"Specifically,":[182],"on":[185],"observed":[187,225],"occurs,":[189],"initially":[191],"see":[192],"improvement":[193],"well":[196],"learned":[199],"can":[201],"used":[203],"differentiate":[205],"during":[212],"net's":[214],"training.":[215],"However,":[216],"continues":[219],"improve":[221],"discrimination":[222],"classes,":[226],"codes":[232],"either":[233],"remains":[234],"steady,":[235],"undergoes":[237],"degradation.":[239],"degradation":[241],"overtraining":[246],"one":[248],"tries":[250],"guard":[252],"against":[253],"net.":[258]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}