{"id":"https://openalex.org/W7058198345","doi":null,"title":"Multi-LSTM Acceleration and CNN Fault Tolerance","display_name":"Multi-LSTM Acceleration and CNN Fault Tolerance","alternate_titles":[],"publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W7058198345"},"language":"en","primary_location":{"id":"pmh:oai:research.chalmers.se:522996","doi":null,"is_oa":true,"landing_page_url":"https://research.chalmers.se/en/publication/522996","pdf_url":"https://research.chalmers.se/publication/522996/file/522996_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W7058198345"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.chalmers.se/publication/522996/file/522996_Fulltext.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ribes, Stefano","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Ribes, Stefano","raw_affiliation_strings":["Chalmers University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology","institution_ids":["https://openalex.org/I66862912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66862912"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":92},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6133000254631042,"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":0.6133000254631042,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.218299999833107,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.03020000085234642,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fpga","display_name":"FPGA","score":0.6060000061988831},{"id":"https://openalex.org/keywords/memory-footprint-reduction","display_name":"memory footprint reduction","score":0.5649999976158142},{"id":"https://openalex.org/keywords/model-mapping","display_name":"model mapping","score":0.4490000009536743},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7850000262260437},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"fault tolerance","score":0.9010000228881836},{"id":"https://openalex.org/keywords/parameter-compression","display_name":"parameter compression","score":0.5789999961853027},{"id":"https://openalex.org/keywords/weight-pruning","display_name":"weight pruning","score":0.8500000238418579},{"id":"https://openalex.org/keywords/weight-clustering","display_name":"weight clustering","score":0.875},{"id":"https://openalex.org/keywords/weight-quantization","display_name":"weight quantization","score":0.9940000176429749},{"id":"https://openalex.org/keywords/error-correcting-codes","display_name":"error-correcting codes","score":0.8960000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453999757766724},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317999720573425},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.26820001006126404},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:research.chalmers.se:522996","doi":null,"is_oa":true,"landing_page_url":"https://research.chalmers.se/en/publication/522996","pdf_url":"https://research.chalmers.se/publication/522996/file/522996_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:research.chalmers.se:522996","doi":null,"is_oa":true,"landing_page_url":"https://research.chalmers.se/en/publication/522996","pdf_url":"https://research.chalmers.se/publication/522996/file/522996_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2626973862","display_name":"Energy-efficient Heterogeneous COmputing at exaSCALE","funder_award_id":"671632","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G667776622","display_name":"Secure Hardware-Software Architectures for Robust Computing Systems","funder_award_id":"644571","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6839706732","display_name":"Meeting Challenges in Computer Architecture","funder_award_id":"340328","funder_id":"https://openalex.org/F4320338352","funder_display_name":"FP7 Ideas: European Research Council"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338352","display_name":"FP7 Ideas: European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7058198345.pdf","grobid_xml":"https://content.openalex.org/works/W7058198345.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1523493493","https://openalex.org/W1536680647","https://openalex.org/W1665214252","https://openalex.org/W1689711448","https://openalex.org/W1895577753","https://openalex.org/W1909234690","https://openalex.org/W1950788856","https://openalex.org/W1980782134","https://openalex.org/W1985340652","https://openalex.org/W2002555321","https://openalex.org/W2094756095","https://openalex.org/W2106033855","https://openalex.org/W2112796928","https://openalex.org/W2119144962","https://openalex.org/W2155428879","https://openalex.org/W2155893237","https://openalex.org/W2294543795","https://openalex.org/W2513568085","https://openalex.org/W2525778437","https://openalex.org/W2529096783","https://openalex.org/W2585720638","https://openalex.org/W2588448445","https://openalex.org/W2589086007","https://openalex.org/W2606294640","https://openalex.org/W2611966310","https://openalex.org/W2612707971","https://openalex.org/W2727238169","https://openalex.org/W2748789698","https://openalex.org/W2750384547","https://openalex.org/W2754815949","https://openalex.org/W2757698722","https://openalex.org/W2762654171","https://openalex.org/W2767260595","https://openalex.org/W2784105695","https://openalex.org/W2793950911","https://openalex.org/W2809188712","https://openalex.org/W2810861508","https://openalex.org/W2827334269","https://openalex.org/W2884928907","https://openalex.org/W2901848761","https://openalex.org/W2903582334","https://openalex.org/W2915106038","https://openalex.org/W2942091739","https://openalex.org/W2943220429","https://openalex.org/W2946206667","https://openalex.org/W2946801000","https://openalex.org/W2950752421","https://openalex.org/W2955092019","https://openalex.org/W2963568120","https://openalex.org/W2964108906","https://openalex.org/W2964335273","https://openalex.org/W2981860227","https://openalex.org/W2982373636","https://openalex.org/W2996351509","https://openalex.org/W2997106510","https://openalex.org/W3006163154","https://openalex.org/W3010156474","https://openalex.org/W3041816437","https://openalex.org/W3123290820","https://openalex.org/W4233996382","https://openalex.org/W4242053016","https://openalex.org/W4252979261"],"related_works":["https://openalex.org/W3162668143","https://openalex.org/W3015938040","https://openalex.org/W4291214119","https://openalex.org/W4401246938","https://openalex.org/W3138915981","https://openalex.org/W2940345045","https://openalex.org/W3133320377","https://openalex.org/W2962820060","https://openalex.org/W7170073157","https://openalex.org/W4383749544"],"abstract_inverted_index":{"This":[0],"thesis":[1,116,268],"addresses":[2,117],"the":[3,9,14,27,118,140,144,148,166,174,228,250,277,312],"following":[4],"two":[5],"problems":[6],"related":[7],"to":[8,41,70,125,139,160,201,208,226,258,264,275,308,320],"field":[10],"of":[11,16,30,78,94,100,114,120,158,169,177,253,324],"Machine":[12],"Learning:":[13],"acceleration":[15],"multiple":[17,81,101,122,152],"Long":[18],"Short":[19],"Term":[20],"Memory":[21],"(LSTM)":[22],"models":[23,83,124],"on":[24,103],"FPGAs":[25],"and":[26,89,245,288],"fault":[28,175],"tolerance":[29,176],"compressed":[31,299],"Convolutional":[32],"Neural":[33],"Networks":[34],"(CNN).":[35],"LSTMs":[36,102,153],"represent":[37,185],"an":[38,254,273],"effective":[39,180],"solution":[40,188],"capture":[42],"long-term":[43],"dependencies":[44],"in":[45,50,57,64,76,86,189,322],"sequential":[46],"data,":[47],"like":[48],"sentences":[49],"Natural":[51],"Language":[52],"Processing":[53],"applications,":[54],"video":[55],"frames":[56],"Scene":[58],"Labeling":[59],"tasks":[60],"or":[61],"temporal":[62],"series":[63],"Time":[65],"Series":[66],"Forecasting.":[67],"In":[68,165,205,224],"order":[69,225],"further":[71],"boost":[72],"their":[73,95,135,202,209,214,233,303],"efficacy,":[74],"especially":[75],"presence":[77,323],"long":[79],"sequences,":[80],"LSTM":[82,123],"are":[84],"utilized":[85],"a":[87,104,126,131,155,186,196,221,282],"Hierarchical":[88],"Stacked":[90],"fashion.":[91],"However,":[92,248],"because":[93],"memory-bounded":[96],"nature,":[97],"efficient":[98],"mapping":[99,121],"computing":[105],"device":[106,128],"becomes":[107,220],"even":[108],"more":[109,262],"challenging.":[110],"The":[111],"first":[112],"part":[113,168],"this":[115,170,267],"problem":[119],"FPGA":[127],"by":[129,310],"introducing":[130],"framework":[132,150],"that":[133,284,298],"modifies":[134],"memory":[136,218,251,293,304],"requirements":[137],"according":[138],"target":[141],"architecture.":[142,183],"For":[143,266],"similar":[145],"accuracy":[146,317],"loss,":[147],"proposed":[149],"maps":[151],"with":[154],"performance":[156,198,222],"improvement":[157],"3x":[159],"5x":[161],"over":[162],"state-of-the-art":[163],"approaches.":[164],"second":[167],"thesis,":[171],"we":[172,270],"investigate":[173],"CNNs,":[178,300],"another":[179],"deep":[181],"learning":[182],"CNNs":[184],"dominating":[187],"image":[190],"classification":[191],"tasks,":[192],"but":[193],"suffer":[194],"from":[195,216],"high":[197],"cost,":[199],"due":[200,207],"computational":[203],"structure.":[204],"fact,":[206],"large":[210],"parameter":[211],"space,":[212],"fetching":[213],"data":[215,260],"main":[217],"typically":[219],"bottleneck.":[223],"tackle":[227],"problem,":[229],"various":[230],"techniques":[231],"for":[232,279,291],"parameters":[234],"compression":[235,314],"have":[236,271,302],"been":[237],"developed,":[238],"such":[239],"as":[240],"weight":[241,243,246],"pruning,":[242],"clustering":[244],"quantization.":[247],"reducing":[249],"footprint":[252,305],"application":[255],"can":[256],"lead":[257],"its":[259],"becoming":[261],"sensitive":[263],"faults.":[265,328],"work,":[269],"conducted":[272],"analysis":[274],"verify":[276],"conditions":[278],"applying":[280],"OddECC,":[281],"mechanism":[283],"supports":[285],"variable":[286],"strength":[287],"size":[289],"ECCs":[290],"different":[292],"regions.":[294],"Our":[295],"experiments":[296],"reveal":[297],"which":[301],"reduced":[306],"up":[307,319],"86.3x":[309],"utilizing":[311],"aforementioned":[313],"schemes,":[315],"exhibit":[316],"drops":[318],"13.56%":[321],"random":[325],"single":[326],"bit":[327]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7058198345","counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2025-10-10T00:00:00"}
