{"id":"https://openalex.org/W2772617276","doi":"https://doi.org/10.1109/iecon.2017.8217476","title":"Enabling high performance deep learning networks on embedded systems","display_name":"Enabling high performance deep learning networks on embedded systems","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2772617276","doi":"https://doi.org/10.1109/iecon.2017.8217476","mag":"2772617276"},"language":"en","primary_location":{"id":"doi:10.1109/iecon.2017.8217476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon.2017.8217476","pdf_url":null,"source":{"id":"https://openalex.org/S4363608531","display_name":"IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100340627","display_name":"Qian Li","orcid":"https://orcid.org/0000-0002-8308-9551"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Li","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057484285","display_name":"Qingcheng Xiao","orcid":"https://orcid.org/0000-0001-6230-5342"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcheng Xiao","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Peking University, Beijing, Beijing, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.628,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93286148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8405","last_page":"8410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T12303","display_name":"Tensor decomposition and applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9973999857902527,"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":0.8380632400512695},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6712182760238647},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5548758506774902},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5090450644493103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5065504312515259},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4816802442073822},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4714142978191376},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46686792373657227},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4202724099159241},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36809688806533813},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36263036727905273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8380632400512695},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6712182760238647},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5548758506774902},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5090450644493103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5065504312515259},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4816802442073822},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4714142978191376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46686792373657227},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4202724099159241},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36809688806533813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36263036727905273},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon.2017.8217476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon.2017.8217476","pdf_url":null,"source":{"id":"https://openalex.org/S4363608531","display_name":"IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.550000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W566555209","https://openalex.org/W1935978687","https://openalex.org/W1983364832","https://openalex.org/W1984020445","https://openalex.org/W2138019504","https://openalex.org/W2145339207","https://openalex.org/W2148542244","https://openalex.org/W2155893237","https://openalex.org/W2157881433","https://openalex.org/W2158899491","https://openalex.org/W2163605009","https://openalex.org/W2460144244","https://openalex.org/W2605258629","https://openalex.org/W2772753951","https://openalex.org/W2950094539","https://openalex.org/W2952230511","https://openalex.org/W2963000224","https://openalex.org/W2963674932","https://openalex.org/W6640289440","https://openalex.org/W6683738474","https://openalex.org/W6684191040","https://openalex.org/W6725543821","https://openalex.org/W6746281611"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973","https://openalex.org/W4390846322"],"abstract_inverted_index":{"Deep":[0],"learning":[1,50,102],"is":[2,37,42],"nowadays":[3],"one":[4],"of":[5,20,54,79,87,135,147,154,173,201,205],"the":[6,17,32,62,72,77,84,95,110,115,145,152,164,171,174,199,203,209],"most":[7],"popular":[8],"research":[9,35],"topics":[10],"in":[11],"computer":[12,33],"science.":[13],"In":[14,90],"recent":[15],"years,":[16],"extensive":[18],"application":[19],"convolutional":[21,123],"neural":[22,111,124],"network":[23,51,80,103,112],"has":[24,82],"made":[25],"it":[26],"become":[27,83],"a":[28,43,133,159],"new":[29],"direction":[30],"for":[31,104],"architecture":[34],"that":[36,186],"developing":[38],"rapidly.":[39],"Currently,":[40],"there":[41],"growing":[44],"demand":[45],"on":[46,52,68,117,122,170,182],"off-line":[47],"deploying":[48],"deep":[49,101],"top":[53],"embedded":[55,69,105,118],"mobile":[56,155],"systems.":[57],"However,":[58],"how":[59],"to":[60,98,138,161,193],"balance":[61],"limited":[63],"computing":[64],"and":[65,71,114,131,176,197],"storage":[66,74,140,210],"resources":[67],"platforms,":[70],"huge":[73],"requirements":[75],"with":[76],"increase":[78],"complexity,":[81],"core":[85],"problem":[86],"current":[88],"research.":[89],"this":[91],"paper,":[92],"we":[93,127,157],"explore":[94,144],"optimization":[96],"technology":[97],"enable":[99],"high-performance":[100],"systems":[106],"from":[107,151],"two":[108],"aspects:":[109],"design":[113],"acceleration":[116],"platforms.":[119],"We":[120,142],"focus":[121],"networks.":[125],"First,":[126],"combine":[128],"several":[129],"technologies":[130],"propose":[132,158],"set":[134],"pruning":[136],"mechanisms":[137],"save":[139],"resources.":[141],"also":[143],"concept":[146],"block-wise":[148],"sparsity.":[149],"Second,":[150],"perspective":[153],"deployment,":[156],"method":[160],"automatically":[162],"select":[163],"optimal":[165],"convolution/matrix":[166],"multiplication":[167],"approach":[168,188],"based":[169],"sparsity":[172],"matrix":[175],"its":[177],"sparse":[178],"structure.":[179],"Our":[180],"experiments":[181],"NVIDIA":[183],"TX1":[184],"show":[185],"our":[187],"can":[189],"be":[190],"used":[191],"together":[192],"promote":[194],"each":[195],"other":[196],"achieve":[198],"goal":[200],"improving":[202],"performance":[204],"computation":[206],"while":[207],"reducing":[208],"consumption.":[211]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}