{"id":"https://openalex.org/W4386568792","doi":"https://doi.org/10.1145/3609093","title":"BitSET: Bit-Serial Early Termination for Computation Reduction in Convolutional Neural Networks","display_name":"BitSET: Bit-Serial Early Termination for Computation Reduction in Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-09-09","ids":{"openalex":"https://openalex.org/W4386568792","doi":"https://doi.org/10.1145/3609093"},"language":"en","primary_location":{"id":"doi:10.1145/3609093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609093","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-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/A5070919323","display_name":"Yunjie Pan","orcid":"https://orcid.org/0009-0002-9351-431X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunjie Pan","raw_affiliation_strings":["University of Michigan, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008163714","display_name":"Jiecao Yu","orcid":"https://orcid.org/0000-0003-2085-0312"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiecao Yu","raw_affiliation_strings":["Facebook Inc., USA"],"affiliations":[{"raw_affiliation_string":"Facebook Inc., USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070401389","display_name":"Andrew Lukefahr","orcid":"https://orcid.org/0009-0003-1167-3999"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Lukefahr","raw_affiliation_strings":["Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027544576","display_name":"Reetuparna Das","orcid":"https://orcid.org/0000-0002-5894-8342"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reetuparna Das","raw_affiliation_strings":["University of Michigan, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["University of Michigan, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070919323"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":1.324,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82962391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"22","issue":"5s","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9968000054359436,"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":0.8755566477775574},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8305039405822754},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7855135202407837},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6897841095924377},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6214693188667297},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6051700711250305},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5738798975944519},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5037936568260193},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.48578694462776184},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45747044682502747},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43955540657043457},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4103655517101288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23059019446372986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755566477775574},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8305039405822754},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7855135202407837},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6897841095924377},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6214693188667297},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6051700711250305},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5738798975944519},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5037936568260193},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.48578694462776184},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45747044682502747},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43955540657043457},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4103655517101288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23059019446372986},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3609093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609093","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W28988658","https://openalex.org/W1836465849","https://openalex.org/W1921523184","https://openalex.org/W2004455575","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2119144962","https://openalex.org/W2123045220","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2319920447","https://openalex.org/W2337344472","https://openalex.org/W2469490737","https://openalex.org/W2560674852","https://openalex.org/W2593245696","https://openalex.org/W2604272474","https://openalex.org/W2657126969","https://openalex.org/W2707890836","https://openalex.org/W2808648285","https://openalex.org/W2809624076","https://openalex.org/W2895531329","https://openalex.org/W2932154853","https://openalex.org/W2952682304","https://openalex.org/W2962818002","https://openalex.org/W2964228333","https://openalex.org/W2999905431","https://openalex.org/W3024621361","https://openalex.org/W3114479342","https://openalex.org/W3129093240","https://openalex.org/W3139340366","https://openalex.org/W4230315356","https://openalex.org/W4233429846","https://openalex.org/W4234552385","https://openalex.org/W4236868170","https://openalex.org/W4237249260","https://openalex.org/W4244471710","https://openalex.org/W4245659846","https://openalex.org/W4287363917","https://openalex.org/W4293584584","https://openalex.org/W4301409532","https://openalex.org/W4320930577","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6746023985","https://openalex.org/W6750227808"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W179829755"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"performance":[7],"across":[8],"a":[9,52,76,92,113,170],"wide":[10],"range":[11],"of":[12,25,103,189],"machine":[13],"learning":[14],"tasks.":[15],"However,":[16],"the":[17,23,44,100,109,127,133,140,177,184],"high":[18],"accuracy":[19,166,179],"usually":[20,49],"comes":[21],"at":[22],"cost":[24],"substantial":[26],"computation":[27,102,129],"and":[28,39,138,159,192],"energy":[29,83,161,194],"consumption,":[30],"making":[31],"it":[32],"difficult":[33],"to":[34,60,146,169,181,186],"be":[35],"deployed":[36],"on":[37],"mobile":[38],"embedded":[40],"devices.":[41],"In":[42],"CNNs,":[43],"compute-intensive":[45],"convolutional":[46],"layers":[47],"are":[48],"followed":[50],"by":[51],"ReLU":[53],"activation":[54,65],"layer,":[55],"which":[56],"clamps":[57],"negative":[58,104],"outputs":[59,105],"zeros,":[61],"resulting":[62],"in":[63,71,132,139,173],"large":[64],"sparsity.":[66],"By":[67],"exploiting":[68],"such":[69],"sparsity":[70],"CNN":[72,85,151],"models,":[73],"we":[74,111],"propose":[75,112],"software-hardware":[77],"co-design":[78],"BitSET,":[79],"that":[80,98,117],"aggressively":[81],"saves":[82],"during":[84],"inference.":[86],"The":[87],"bit-serial":[88,143,150],"BitSET":[89,125,153],"accelerator":[90],"adopts":[91],"prediction-based":[93],"bit-level":[94,128,174],"early":[95,135],"termination":[96,136],"technique":[97],"terminates":[99],"ineffectual":[101],"early.":[106],"To":[107],"assist":[108],"algorithm,":[110],"novel":[114],"weight":[115],"encoding":[116],"allows":[118],"more":[119],"accurate":[120],"predictions":[121],"with":[122,164],"fewer":[123],"bits.":[124],"leverages":[126],"reduction":[130,172],"both":[131],"predictive":[134],"algorithm":[137],"non-predictive,":[141],"energy-efficient":[142,149],"architecture.":[144],"Compared":[145],"UNPU,":[147],"an":[148,155,187],"accelerator,":[152],"yields":[154],"average":[156,188],"1.5\u00d7":[157],"speedup":[158,191],"1.4\u00d7":[160,193],"efficiency":[162,195],"improvement":[163],"no":[165],"loss":[167,180],"due":[168],"48%":[171],"computations.":[175],"Relaxing":[176],"allowed":[178],"1%":[182],"increases":[183],"gains":[185],"1.6\u00d7":[190],"improvement.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}