{"id":"https://openalex.org/W4402349228","doi":"https://doi.org/10.1145/3665314.3670836","title":"ePredictNet: Low Cost Error Prediction Neural Network","display_name":"ePredictNet: Low Cost Error Prediction Neural Network","publication_year":2024,"publication_date":"2024-08-05","ids":{"openalex":"https://openalex.org/W4402349228","doi":"https://doi.org/10.1145/3665314.3670836"},"language":"en","primary_location":{"id":"doi:10.1145/3665314.3670836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665314.3670836","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665314.3670836?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3665314.3670836?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092705452","display_name":"Georgios Chatzitsompanis","orcid":"https://orcid.org/0000-0002-3358-7181"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Chatzitsompanis","raw_affiliation_strings":["Queen's University Belfast, Belfast, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3358-7181","affiliations":[{"raw_affiliation_string":"Queen's University Belfast, Belfast, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077501734","display_name":"Georgios Karakonstantis","orcid":"https://orcid.org/0000-0002-5693-8503"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Karakonstantis","raw_affiliation_strings":["Computer Science, Queen's University Belfast, Belfast, Antrim, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-5693-8503","affiliations":[{"raw_affiliation_string":"Computer Science, Queen's University Belfast, Belfast, Antrim, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126231945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10320","display_name":"Neural Networks and Applications","score":0.9947999715805054,"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":0.9842000007629395,"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/computer-science","display_name":"Computer science","score":0.7001435160636902},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5987503528594971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3396453857421875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001435160636902},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5987503528594971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3396453857421875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3665314.3670836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665314.3670836","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665314.3670836?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/27704979-296a-445d-b81f-1e3737e8301f","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/27704979-296a-445d-b81f-1e3737e8301f","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chatzitsompanis , G & Karakonstantis , G 2024 , ePredictNet: low cost error prediction neural network . in ISLPED '24: proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design . vol. 12 , Association for Computing Machinery , ACM/IEEE International Symposium on Low Power Electronics and Design 2024 , California , United States , 05/08/2024 . https://doi.org/10.1145/3665314.3670836","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3665314.3670836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665314.3670836","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665314.3670836?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4099999964237213,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G2030651639","display_name":"Approximate Computing for Power and Energy Optimisation","funder_award_id":"956090","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402349228.pdf","grobid_xml":"https://content.openalex.org/works/W4402349228.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1437335841","https://openalex.org/W1983545421","https://openalex.org/W2080592089","https://openalex.org/W2096903656","https://openalex.org/W2106648230","https://openalex.org/W2115722171","https://openalex.org/W2133079932","https://openalex.org/W2151802820","https://openalex.org/W2338546029","https://openalex.org/W2565125333","https://openalex.org/W2613791011","https://openalex.org/W2761878354","https://openalex.org/W2766429716","https://openalex.org/W2766888159","https://openalex.org/W2772488910","https://openalex.org/W2809893061","https://openalex.org/W2883238988","https://openalex.org/W2890133646","https://openalex.org/W2913980322","https://openalex.org/W2963029056","https://openalex.org/W2995091922","https://openalex.org/W3013155238","https://openalex.org/W3015806656","https://openalex.org/W3016036342","https://openalex.org/W3092621962","https://openalex.org/W3093982621","https://openalex.org/W3214556856","https://openalex.org/W4205325906","https://openalex.org/W4210604423","https://openalex.org/W4232601843","https://openalex.org/W4285821740","https://openalex.org/W4316135746","https://openalex.org/W4386211331","https://openalex.org/W6670560480"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0],"pursuit":[1],"of":[2,77,118,214,237],"miniature":[3],"energy-efficient":[4],"chips,":[5],"and":[6,31,73,150,156,166,174,232],"push":[7],"for":[8,86,239],"scaled":[9,81],"voltages":[10],"leads":[11],"to":[12,50,115,193,223],"increased":[13],"timing":[14],"errors":[15,38,78,195,241],"that":[16,66,90,112,133],"threaten":[17],"the":[18,75,87,172,212,234],"correct":[19],"system":[20],"functionality.":[21],"Conventional":[22],"error":[23,70,92,142,186,199],"mitigation":[24,200],"schemes":[25],"based":[26,61,179],"on":[27,62,97,128,137],"redundancy,":[28],"require":[29],"costly":[30],"disruptive":[32],"design":[33],"changes,":[34],"while":[35,145],"they":[36,40],"detect":[37],"after":[39],"occur":[41],"requiring":[42],"expensive":[43],"follow":[44],"up":[45],"correction":[46],"schemes.":[47,180,201],"In":[48],"contrast":[49],"existing":[51],"approaches,":[52],"this":[53],"paper":[54],"introduces":[55],"ePredictNet,":[56],"an":[57],"accurate":[58,91],"workload-aware":[59],"error-predictor":[60],"compressed":[63],"neural":[64,110],"networks":[65],"can":[67,124,139,190,210],"estimate":[68],"early":[69],"prone":[71],"instructions":[72,245],"avoid":[74,194],"manifestation":[76],"even":[79],"under":[80,218],"voltages.":[82],"Our":[83,130],"work":[84],"shows":[85],"first":[88],"time":[89],"prediction":[93],"models":[94],"are":[95,246],"realizable":[96],"hardware":[98],"with":[99,152,162,227],"very":[100],"low":[101],"cost.":[102],"This":[103],"is":[104,113],"achieved":[105],"by":[106,177,196],"training":[107],"a":[108,116,163,183,205,215],"quantized":[109],"network":[111],"converted":[114],"netlist":[117],"truth":[119],"tables":[120],"using":[121],"LogicNets,":[122],"which":[123],"efficiently":[125],"be":[126,191],"mapped":[127,136],"circuit.":[129],"results":[131],"indicate,":[132],"ePredictNet":[134,189],"once":[135,160,243],"FPGA":[138],"achieve":[140],"99.39%":[141],"classification":[143],"accuracy":[144],"utilizing":[146],"only":[147,153,242],"270":[148],"LUTs":[149],"comes":[151],"2.1%":[154],"area":[155,173],"5%":[157],"power":[158,175,206,226],"overhead":[159],"integrated":[161],"RISC":[164],"core":[165,217],"costs":[167],"up-to":[168],"98%":[169],"less":[170],"than":[171],"incurred":[176],"redundancy":[178],"Apart":[181],"from":[182],"cost":[184],"effective":[185],"estimation":[187],"scheme,":[188],"used":[192],"guiding":[197],"complimentary":[198],"For":[202],"instance,":[203],"in":[204],"conscious":[207],"use":[208],"case,ePredictNet":[209],"allow":[211],"operation":[213],"Open-RISC":[216],"12%":[219],"reduced":[220],"voltage,":[221],"allowing":[222],"save":[224],"17%":[225],"minimal":[228],"2.7%":[229],"throughput":[230],"reduction":[231],"guide":[233],"dynamic":[235],"relaxation":[236],"frequency":[238],"avoiding":[240],"error-prone":[244],"predicted.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}