{"id":"https://openalex.org/W2802331610","doi":"https://doi.org/10.1109/iscas.2018.8351679","title":"Energy-efficient Convolutional Neural Networks via Statistical Error Compensated Near Threshold Computing","display_name":"Energy-efficient Convolutional Neural Networks via Statistical Error Compensated Near Threshold Computing","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2802331610","doi":"https://doi.org/10.1109/iscas.2018.8351679","mag":"2802331610"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2018.8351679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5019582323","display_name":"Yingyan Lin","orcid":"https://orcid.org/0000-0001-5946-203X"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yingyan Lin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rice University"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085983829","display_name":"Joseph R. Cavallaro","orcid":"https://orcid.org/0000-0002-9841-1806"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph R. Cavallaro","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rice University"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rice University","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019582323"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66666363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9994000196456909,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7909489870071411},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5884097218513489},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5166521668434143},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.41726452112197876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28998062014579773},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09895870089530945},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09422585368156433},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09408760070800781},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06816980242729187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7909489870071411},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5884097218513489},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5166521668434143},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.41726452112197876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28998062014579773},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09895870089530945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09422585368156433},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09408760070800781},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06816980242729187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2018.8351679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1799366690","https://openalex.org/W1973423687","https://openalex.org/W1998525920","https://openalex.org/W2048785750","https://openalex.org/W2067523571","https://openalex.org/W2102545063","https://openalex.org/W2110910865","https://openalex.org/W2112796928","https://openalex.org/W2113145298","https://openalex.org/W2127218421","https://openalex.org/W2160929292","https://openalex.org/W2289252105","https://openalex.org/W2346708235","https://openalex.org/W2538834887","https://openalex.org/W2546302380","https://openalex.org/W2566876368","https://openalex.org/W3024621361","https://openalex.org/W4249427977","https://openalex.org/W6638444622","https://openalex.org/W6663353324","https://openalex.org/W6678914141"],"related_works":["https://openalex.org/W2748454020","https://openalex.org/W2998526951","https://openalex.org/W3119610945","https://openalex.org/W2735477435","https://openalex.org/W3181746755","https://openalex.org/W2521062615","https://openalex.org/W2901465038","https://openalex.org/W3090822330","https://openalex.org/W2749468216","https://openalex.org/W4239686595"],"abstract_inverted_index":{"There":[0],"has":[1,59],"been":[2,60],"a":[3,37,47,85,116,123],"growing":[4],"need":[5],"for":[6,88,98],"deploying":[7],"machine":[8],"learning":[9],"algorithms":[10],"such":[11],"as":[12],"convolutional":[13],"neural":[14],"networks":[15],"(CNNs)":[16],"on":[17],"resource-constrained":[18],"edge":[19],"platforms":[20],"to":[21,62,75,135,178],"enable":[22],"on-device":[23],"local":[24],"inference.":[25],"Despite":[26],"CNNs'":[27],"excellent":[28],"performance":[29,72],"that":[30,111,153],"approaches":[31],"and":[32,122,175],"sometimes":[33],"exceeds":[34],"humans":[35],"in":[36,94,130,140,148,161,181,193],"large":[38],"variety":[39],"of":[40,70,91,185],"tasks,":[41],"their":[42],"often":[43],"prohibitive":[44],"complexity":[45],"remains":[46],"major":[48],"inhibitor.":[49],"To":[50],"address":[51],"the":[52,68,95,131,143,154,162,166,182,194],"energy":[53,65,99],"challenge,":[54],"near":[55],"threshold":[56],"computing":[57],"(NTC)":[58],"proposed":[61,155,167],"aggressively":[63],"reduce":[64,136],"consumption,":[66],"at":[67],"cost":[69],"increased":[71],"variation":[73,171],"due":[74],"circuit":[76],"level":[77],"statistical":[78],"behavior.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,102],"propose":[84],"variation-tolerant":[86],"architecture":[87,156],"CNNs":[89,105,141,159],"capable":[90],"robust":[92,104,158],"operations":[93],"NTC":[96,117,163],"regime":[97],"efficiency.":[100],"Specifically,":[101,165],"construct":[103],"from":[106],"two":[107],"low-cost":[108],"unreliable":[109],"designs":[110],"have":[112],"different":[113],"error":[114],"statistics:":[115],"design":[118,126],"with":[119],"full":[120],"precision,":[121],"K-means":[124],"approximated":[125],"where":[127],"weight":[128],"vectors":[129],"CNN":[132,168],"are":[133],"clustered":[134],"complexity.":[137],"When":[138],"evaluated":[139],"using":[142],"MNIST":[144],"dataset,":[145],"simulation":[146],"results":[147],"45":[149],"nm":[150],"CMOS":[151],"show":[152],"enables":[157],"operating":[160],"regime.":[164],"can":[169],"enhance":[170],"tolerance":[172],"by":[173],"10\u00d7":[174],"achieve":[176],"up":[177],"134\u00d7":[179],"reduction":[180],"standard":[183],"deviation":[184],"inference":[186,196],"accuracy":[187],"Pdet":[188],"while":[189],"incurring":[190],"marginal":[191],"degradation":[192],"median":[195],"accuracy.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"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"}