{"id":"https://openalex.org/W2942386945","doi":"https://doi.org/10.1109/isqed.2019.8697843","title":"Dynamic Reconfiguration of CNNs for Input-Dependent Approximation","display_name":"Dynamic Reconfiguration of CNNs for Input-Dependent Approximation","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2942386945","doi":"https://doi.org/10.1109/isqed.2019.8697843","mag":"2942386945"},"language":"en","primary_location":{"id":"doi:10.1109/isqed.2019.8697843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed.2019.8697843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Symposium on Quality Electronic Design (ISQED)","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/A5021040269","display_name":"Maedeh Hemmat","orcid":"https://orcid.org/0000-0002-0085-4589"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maedeh Hemmat","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072204999","display_name":"Azadeh Davoodi","orcid":"https://orcid.org/0000-0001-5213-2556"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azadeh Davoodi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021040269"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.4049,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64010287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"105","issue":null,"first_page":"176","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.8933780789375305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850906252861023},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7218201756477356},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6779905557632446},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6129094362258911},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5533424019813538},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.5026769638061523},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4755506217479706},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.44831162691116333},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.42708516120910645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3545148968696594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30925509333610535},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22654390335083008}],"concepts":[{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.8933780789375305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850906252861023},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7218201756477356},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6779905557632446},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6129094362258911},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5533424019813538},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.5026769638061523},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4755506217479706},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.44831162691116333},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.42708516120910645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3545148968696594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30925509333610535},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22654390335083008},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isqed.2019.8697843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed.2019.8697843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Symposium on Quality Electronic Design (ISQED)","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":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1537260300","https://openalex.org/W1998917233","https://openalex.org/W2010202670","https://openalex.org/W2094756095","https://openalex.org/W2111162011","https://openalex.org/W2133796295","https://openalex.org/W2495046539","https://openalex.org/W2518281301","https://openalex.org/W2563860341","https://openalex.org/W2611289746","https://openalex.org/W2791845808","https://openalex.org/W2963674932","https://openalex.org/W3105248137","https://openalex.org/W4243519499","https://openalex.org/W4243928383","https://openalex.org/W4245873651","https://openalex.org/W6674479107","https://openalex.org/W6730589793","https://openalex.org/W6737660084","https://openalex.org/W6749551813","https://openalex.org/W6825195337"],"related_works":["https://openalex.org/W2808484818","https://openalex.org/W2810427553","https://openalex.org/W2135053878","https://openalex.org/W2941434274","https://openalex.org/W2340647897","https://openalex.org/W4249632163","https://openalex.org/W1760305469","https://openalex.org/W2797161794","https://openalex.org/W2073075351","https://openalex.org/W2096938998"],"abstract_inverted_index":{"In":[0,154],"this":[1],"work,":[2],"we":[3,99,160],"propose":[4,138],"a":[5,51,149,178],"novel":[6],"framework":[7,48,118,145],"which":[8,103,119],"enables":[9,25],"dynamic":[10],"reconfiguration":[11,24],"of":[12,28,53,80,92,124,148,180,187],"an":[13,116],"already-trained":[14],"Convolutional":[15],"Neural":[16],"Network":[17],"(CNN)":[18],"in":[19,38,107,169],"hardware":[20,140],"during":[21],"inference.":[22,70],"The":[23],"input-dependent":[26],"approximation":[27],"the":[29,54,63,69,93,108,181,185,188],"CNN":[30,109,152],"to":[31,67,77,142,173],"achieve":[32,96],"power":[33,72,163],"saving":[34,73,164],"without":[35],"much":[36],"degradation":[37,168],"its":[39],"classification":[40,170],"accuracy":[41,171],"at":[42],"run-time.":[43],"For":[44],"each":[45,133],"input,":[46],"our":[47,144,155],"uses":[49],"only":[50,177],"fraction":[52,179],"CNN's":[55],"edge":[56,182],"weights":[57,106,125,183],"based":[58,110],"on":[59,111,146],"that":[60],"input":[61],"(with":[62],"rest":[64],"remaining":[65],"0)":[66],"conduct":[68],"Consequently,":[71],"is":[74],"possible":[75],"due":[76,172],"fewer":[78,88],"number":[79],"fetches":[81],"from":[82,129],"off-chip":[83,130],"memory":[84,131],"as":[85,87],"well":[86],"multiplications":[89],"for":[90,132,184],"majority":[91,186],"inputs.":[94,189],"To":[95],"per-input":[97],"approximation,":[98],"use":[100],"clustering":[101],"algorithm":[102],"groups":[104],"similar":[105],"their":[112],"importance,":[113],"and":[114],"design":[115],"iterative":[117],"decides":[120],"how":[121],"many":[122],"clusters":[123],"should":[126],"be":[127],"fetched":[128],"individual":[134],"input.":[135],"We":[136],"also":[137],"new":[139],"structures":[141],"implement":[143],"top":[147],"recently-proposed":[150],"FPGA-based":[151],"accelerator.":[153],"experiments":[156],"with":[157,165,176],"popular":[158],"CNNs,":[159],"show":[161],"significant":[162],"almost":[166],"no":[167],"doing":[174],"inference":[175]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}