{"id":"https://openalex.org/W3094157122","doi":"https://doi.org/10.1109/mlsp49062.2020.9231550","title":"Self-Compression in Bayesian Neural Networks","display_name":"Self-Compression in Bayesian Neural Networks","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W3094157122","doi":"https://doi.org/10.1109/mlsp49062.2020.9231550","mag":"3094157122"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp49062.2020.9231550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp49062.2020.9231550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5091354847","display_name":"Giuseppina Carannante","orcid":null},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Giuseppina Carannante","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068906628","display_name":"Dimah Dera","orcid":"https://orcid.org/0000-0002-7168-5858"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimah Dera","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045996251","display_name":"Ghulam Rasool","orcid":"https://orcid.org/0000-0001-8551-0090"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghulam Rasool","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041401460","display_name":"Nidhal Bouaynaya","orcid":"https://orcid.org/0000-0002-8833-8414"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nidhal C. Bouaynaya","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ","institution_ids":["https://openalex.org/I44265643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091354847"],"corresponding_institution_ids":["https://openalex.org/I44265643"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55472795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"37","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9965999722480774,"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":0.9965999722480774,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9958999752998352,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9955999851226807,"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":0.8492242097854614},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7472717761993408},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6559341549873352},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.6244469285011292},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5472150444984436},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5302025079727173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.526890754699707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49081215262413025},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.46474024653434753},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4500824809074402},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.44307300448417664},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4384094774723053},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.43087801337242126},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.4142359495162964},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.32356250286102295},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21074983477592468},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10840249061584473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492242097854614},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7472717761993408},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6559341549873352},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.6244469285011292},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5472150444984436},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5302025079727173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526890754699707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49081215262413025},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.46474024653434753},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4500824809074402},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.44307300448417664},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4384094774723053},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.43087801337242126},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.4142359495162964},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32356250286102295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21074983477592468},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10840249061584473},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp49062.2020.9231550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp49062.2020.9231550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2141436875","display_name":null,"funder_award_id":"EP/T013265/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1902934009","https://openalex.org/W2007339694","https://openalex.org/W2108677974","https://openalex.org/W2119144962","https://openalex.org/W2120432001","https://openalex.org/W2123469553","https://openalex.org/W2164411961","https://openalex.org/W2168231600","https://openalex.org/W2182396527","https://openalex.org/W2276892413","https://openalex.org/W2300242332","https://openalex.org/W2520760693","https://openalex.org/W2750384547","https://openalex.org/W2808181858","https://openalex.org/W2904908132","https://openalex.org/W2951266961","https://openalex.org/W2962770929","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963114950","https://openalex.org/W2964299589","https://openalex.org/W2991229825","https://openalex.org/W2995655856","https://openalex.org/W2998218113","https://openalex.org/W3035323010","https://openalex.org/W6637242042","https://openalex.org/W6639703010","https://openalex.org/W6676315081","https://openalex.org/W6684859321","https://openalex.org/W6725543821","https://openalex.org/W6764214684"],"related_works":["https://openalex.org/W3106461837","https://openalex.org/W4283700523","https://openalex.org/W3168182983","https://openalex.org/W4387079005","https://openalex.org/W4321472004","https://openalex.org/W4221166418","https://openalex.org/W2968265130","https://openalex.org/W3117893869","https://openalex.org/W2973085194","https://openalex.org/W1723534789"],"abstract_inverted_index":{"Machine":[0],"learning":[1,25],"models":[2],"have":[3],"achieved":[4],"human-level":[5],"performance":[6,45],"on":[7,30],"various":[8],"tasks.":[9],"This":[10],"success":[11],"comes":[12],"at":[13],"a":[14,78],"high":[15],"cost":[16],"of":[17,42,49,65,109,114,142],"computation":[18],"and":[19,53],"storage":[20],"overhead,":[21],"which":[22,103],"makes":[23],"machine":[24],"algorithms":[26],"difficult":[27],"to":[28,36,106],"deploy":[29],"edge":[31],"devices.":[32],"Typically,":[33],"one":[34],"has":[35],"partially":[37],"sacrifice":[38],"accuracy":[39],"in":[40,47,97],"favor":[41],"an":[43],"increased":[44],"quantified":[46],"terms":[48],"reduced":[50],"memory":[51],"usage":[52],"energy":[54],"consumption.":[55],"Current":[56],"methods":[57],"compress":[58],"the":[59,63,66,85,107,112,115,122,134,139],"networks":[60,93],"by":[61,69,129,133],"reducing":[62],"precision":[64],"parameters":[67,131],"or":[68],"eliminating":[70],"redundant":[71],"ones.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"propose":[77],"new":[79],"insight":[80],"into":[81],"network":[82,123,135],"compression":[83],"through":[84,111],"Bayesian":[86,91],"framework.":[87],"We":[88],"show":[89,120],"that":[90,121],"neural":[92],"automatically":[94],"discover":[95],"redundancy":[96],"model":[98],"parameters,":[99],"thus":[100],"enabling":[101],"self-compression,":[102],"is":[104],"linked":[105],"propagation":[108],"uncertainty":[110],"layers":[113],"network.":[116],"Our":[117],"experimental":[118],"results":[119],"architecture":[124],"can":[125],"be":[126],"successfully":[127],"compressed":[128],"deleting":[130],"identified":[132],"itself":[136],"while":[137],"retaining":[138],"same":[140],"level":[141],"accuracy.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}