{"id":"https://openalex.org/W2990873889","doi":"https://doi.org/10.1145/3349567.3351721","title":"BPNet: Branch-pruned conditional neural network for systematic time-accuracy tradeoff in DNN inference","display_name":"BPNet: Branch-pruned conditional neural network for systematic time-accuracy tradeoff in DNN inference","publication_year":2019,"publication_date":"2019-10-13","ids":{"openalex":"https://openalex.org/W2990873889","doi":"https://doi.org/10.1145/3349567.3351721","mag":"2990873889"},"language":"en","primary_location":{"id":"doi:10.1145/3349567.3351721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3349567.3351721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Hardware/Software Codesign and System Synthesis Companion","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/A5079603105","display_name":"Kyungchul Park","orcid":"https://orcid.org/0000-0001-6742-8894"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyungchul Park","raw_affiliation_strings":["University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029634385","display_name":"Youngmin Yi","orcid":"https://orcid.org/0000-0001-9802-2109"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngmin Yi","raw_affiliation_strings":["University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079603105"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55453326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.998199999332428,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7785440683364868},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7121009826660156},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6983077526092529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354853272438049},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3885303735733032},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36820757389068604},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34220564365386963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785440683364868},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7121009826660156},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6983077526092529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354853272438049},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3885303735733032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36820757389068604},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34220564365386963}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3349567.3351721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3349567.3351721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Hardware/Software Codesign and System Synthesis Companion","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2022485595","https://openalex.org/W2133796295","https://openalex.org/W2773378604","https://openalex.org/W2895298874"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2053286651","https://openalex.org/W2055243143","https://openalex.org/W2181743346","https://openalex.org/W2187401768","https://openalex.org/W2181413294","https://openalex.org/W2989452537","https://openalex.org/W2052122378","https://openalex.org/W2544423928"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"have":[2],"been":[3],"attempts":[4],"to":[5,92,115],"execute":[6],"the":[7,19,22,27,50,77,81,116],"neural":[8,83],"network":[9,84],"conditionally":[10],"with":[11,36,97],"auxiliary":[12,51],"classifiers":[13],"allowing":[14],"early":[15],"termination":[16],"depending":[17],"on":[18,103,112],"difficulty":[20],"of":[21,106],"input,":[23],"which":[24,76],"can":[25,85],"reduce":[26],"execution":[28],"time":[29],"or":[30,35,48,53],"energy":[31],"consumption":[32],"without":[33,108],"any":[34,109],"negligible":[37],"accuracy":[38,110],"decrease.":[39],"However,":[40],"these":[41],"studies":[42],"do":[43],"not":[44],"consider":[45],"how":[46],"many":[47],"where":[49],"classifiers,":[52],"branches,":[54],"should":[55],"be":[56,86],"added":[57],"in":[58,75],"a":[59],"systematic":[60],"fashion.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"Branch-pruned":[67],"Conditional":[68],"Neural":[69],"Network":[70],"(BPNet)":[71],"and":[72,95,99],"its":[73],"methodology":[74],"time-accuracy":[78],"tradeoff":[79],"for":[80],"conditional":[82],"found":[87],"systematically.":[88],"We":[89],"applied":[90],"BPNet":[91,101],"SqueezeNet,":[93],"ResNet-20,":[94],"VGG-16":[96],"CIFAR-10":[98],"100.":[100],"achieves":[102],"average":[104,113],"2.0X":[105],"speedups":[107],"drop":[111],"compared":[114],"base":[117],"network.":[118]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}