{"id":"https://openalex.org/W4293863489","doi":"https://doi.org/10.1109/siu55565.2022.9864848","title":"Using Deep Compression on PyTorch Models for Autonomous Systems","display_name":"Using Deep Compression on PyTorch Models for Autonomous Systems","publication_year":2022,"publication_date":"2022-05-15","ids":{"openalex":"https://openalex.org/W4293863489","doi":"https://doi.org/10.1109/siu55565.2022.9864848"},"language":"en","primary_location":{"id":"doi:10.1109/siu55565.2022.9864848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu55565.2022.9864848","pdf_url":null,"source":{"id":"https://openalex.org/S4363607818","display_name":"2022 30th Signal Processing and Communications Applications Conference (SIU)","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":"2022 30th Signal Processing and Communications Applications Conference (SIU)","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/A5066353644","display_name":"Eren Dogan","orcid":null},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Eren Dogan","raw_affiliation_strings":["Ozyegin University,Istanbul,Turkey","Ozyegin University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ozyegin University,Istanbul,Turkey","institution_ids":["https://openalex.org/I44925452"]},{"raw_affiliation_string":"Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029193455","display_name":"H. Fatih U\u011furda\u011f","orcid":"https://orcid.org/0000-0002-6256-0850"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"H. Fatih Ugurdag","raw_affiliation_strings":["Ozyegin University,Istanbul,Turkey","Ozyegin University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ozyegin University,Istanbul,Turkey","institution_ids":["https://openalex.org/I44925452"]},{"raw_affiliation_string":"Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002636310","display_name":"Hasan Unlu","orcid":null},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hasan Unlu","raw_affiliation_strings":["Ozyegin University,Istanbul,Turkey","Ozyegin University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ozyegin University,Istanbul,Turkey","institution_ids":["https://openalex.org/I44925452"]},{"raw_affiliation_string":"Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44925452"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09249934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.929099977016449,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.929099977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423584461212158},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7342877388000488},{"id":"https://openalex.org/keywords/microcontroller","display_name":"Microcontroller","score":0.6652452945709229},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6074710488319397},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.599558413028717},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5861853361129761},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5362194776535034},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.47360825538635254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46015527844429016},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4220176935195923},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2973589301109314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423584461212158},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7342877388000488},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.6652452945709229},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6074710488319397},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.599558413028717},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5861853361129761},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5362194776535034},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.47360825538635254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46015527844429016},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4220176935195923},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2973589301109314},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/siu55565.2022.9864848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu55565.2022.9864848","pdf_url":null,"source":{"id":"https://openalex.org/S4363607818","display_name":"2022 30th Signal Processing and Communications Applications Conference (SIU)","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":"2022 30th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/8634","is_oa":false,"landing_page_url":"http://hdl.handle.net/10679/8634","pdf_url":null,"source":{"id":"https://openalex.org/S4306400232","display_name":"ECS Journal of Solid State Science and Technology (The Electrochemical Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802273670","host_organization_name":"Electrochemical Society","host_organization_lineage":["https://openalex.org/I2802273670"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3120961607","https://openalex.org/W4401568740","https://openalex.org/W4316095964","https://openalex.org/W3148568549","https://openalex.org/W2098207691","https://openalex.org/W1648516568","https://openalex.org/W361036515","https://openalex.org/W2929170389","https://openalex.org/W4300097863","https://openalex.org/W2950268673"],"abstract_inverted_index":{"Applications":[0],"of":[1,35,48,144],"artificial":[2],"neural":[3,87],"networks":[4],"on":[5,40,81],"low-cost":[6],"embedded":[7],"systems":[8],"and":[9,55,90,105,113,155],"microcontrollers":[10],"(MCUs),":[11],"has":[12],"recently":[13],"been":[14],"attracting":[15],"more":[16,43],"attention":[17],"than":[18],"ever.":[19],"Since":[20],"MCUs":[21,41,53],"have":[22],"limited":[23,29],"memory":[24,149],"capacity":[25],"as":[26,28],"well":[27],"compute-speed":[30],"compared":[31],"to":[32,72,85,101,117],"workstations,":[33],"employment":[34],"current":[36],"deep":[37],"learning":[38],"algorithms":[39],"becomes":[42],"practical":[44,56],"with":[45],"the":[46,97,110,142,145,148,156],"help":[47],"model":[49,67],"compression.":[50],"This":[51],"makes":[52],"common":[54],"alternative":[57],"solution":[58],"for":[59,133],"autonomous":[60],"systems.":[61],"In":[62,141],"this":[63],"paper,":[64],"we":[65,95],"add":[66],"compression,":[68],"specifically":[69],"Deep":[70],"Compression,":[71],"an":[73],"existing":[74],"work,":[75],"which":[76,136],"efficiently":[77],"deploys":[78],"PyTorch":[79],"models":[80],"MCUs,":[82],"in":[83,103],"order":[84],"increase":[86],"network":[88],"speed":[89,158],"save":[91],"electrical":[92],"power.":[93],"First,":[94],"prune":[96],"weight":[98],"values":[99],"close":[100],"zero":[102],"convolutional":[104],"fully":[106],"connected":[107],"layers.":[108],"Secondly,":[109],"remaining":[111],"weights":[112],"activations":[114],"are":[115,127],"quantized":[116],"8-bit":[118],"integers":[119],"from":[120],"32-bit":[121],"floating-point.":[122],"Finally,":[123],"forward":[124],"pass":[125],"functions":[126],"compressed":[128],"using":[129],"special":[130],"data":[131],"structures":[132],"sparse":[134],"matrices,":[135],"store":[137],"only":[138],"nonzero":[139],"weights.":[140],"case":[143],"LeNet-5":[146],"model,":[147],"footprint":[150],"was":[151,159],"reduced":[152],"by":[153,161],"12.5x,":[154],"inference":[157],"boosted":[160],"2.6x.":[162]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2022-09-01T00:00:00"}