{"id":"https://openalex.org/W4399486638","doi":"https://doi.org/10.1145/3649476.3658740","title":"Probabilistic Bayesian Neural Networks for Efficient Inference","display_name":"Probabilistic Bayesian Neural Networks for Efficient Inference","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399486638","doi":"https://doi.org/10.1145/3649476.3658740"},"language":"en","primary_location":{"id":"doi:10.1145/3649476.3658740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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/A5079607802","display_name":"Mohammed Alawad","orcid":"https://orcid.org/0000-0002-7491-0440"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Alawad","raw_affiliation_strings":["Electrical and Computer Engineering, Wayne State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-7491-0440","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Wayne State University, USA","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049865819","display_name":"M. Ishak","orcid":"https://orcid.org/0009-0002-9165-5477"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Ishak","raw_affiliation_strings":["Electrical and Computer Engineering, Wayne State University, USA"],"raw_orcid":"https://orcid.org/0009-0002-9165-5477","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Wayne State University, USA","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185443292"],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4986135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"724","last_page":"729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9970999956130981,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9970999956130981,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9919999837875366,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9908999800682068,"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":0.699634313583374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6119371652603149},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5933798551559448},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5658217668533325},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5186740159988403},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49168092012405396},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.47501835227012634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4735245704650879},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4482637643814087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699634313583374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6119371652603149},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5933798551559448},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5658217668533325},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5186740159988403},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49168092012405396},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.47501835227012634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4735245704650879},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4482637643814087}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649476.3658740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1494192115","https://openalex.org/W2003056114","https://openalex.org/W2112796928","https://openalex.org/W2287585202","https://openalex.org/W2511024728","https://openalex.org/W2903731869","https://openalex.org/W2996034257","https://openalex.org/W3022634314","https://openalex.org/W3035963492","https://openalex.org/W3098989436","https://openalex.org/W4226337850","https://openalex.org/W4308886937","https://openalex.org/W4312036234","https://openalex.org/W4367834757","https://openalex.org/W4387010670"],"related_works":["https://openalex.org/W2163814182","https://openalex.org/W1734881440","https://openalex.org/W2372267530","https://openalex.org/W2969189870","https://openalex.org/W2965643117","https://openalex.org/W4303857162","https://openalex.org/W2407375987","https://openalex.org/W2505726097","https://openalex.org/W2010643158","https://openalex.org/W3049691116"],"abstract_inverted_index":{"Bayesian":[0],"Neural":[1],"Networks":[2],"(BNNs)":[3],"offer":[4],"a":[5,32,146],"principled":[6],"framework":[7],"for":[8,66,166],"modeling":[9],"uncertainty":[10,70],"in":[11,113,127,153,168],"deep":[12],"learning":[13],"tasks.":[14],"However,":[15],"conventional":[16],"BNNs":[17,133],"often":[18],"suffer":[19],"from":[20],"high":[21],"computational":[22,115],"complexity":[23,116],"and":[24,56,93,117,175],"parameter":[25],"overhead.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"propose":[31],"novel":[33],"approach,":[34],"termed":[35],"Probabilistic":[36],"BNN":[37],"(ProbBNN),":[38],"which":[39],"leverages":[40],"probabilistic":[41,110],"computing":[42,174],"principles":[43],"to":[44,80,131,143,159],"streamline":[45],"the":[46,67,72,82,100,123,137,154],"inference":[47,101],"process.":[48],"Unlike":[49],"traditional":[50,132],"deterministic":[51,106],"approaches,":[52,161],"ProbBNN":[53,126,144],"represents":[54],"inputs":[55],"parameters":[57,83,157],"as":[58,172],"random":[59],"variables":[60],"governed":[61],"by":[62,103],"probability":[63],"distributions,":[64],"allowing":[65],"propagation":[68],"of":[69,84,95,125,139,148,151,156],"throughout":[71],"network.":[73],"We":[74],"employ":[75],"Gaussian":[76],"Mixture":[77],"Models":[78],"(GMMs)":[79],"represent":[81],"each":[85],"neuron":[86],"or":[87],"convolutional":[88],"kernel,":[89],"enabling":[90],"efficient":[91],"encoding":[92],"processing":[94],"uncertainty.":[96],"Our":[97],"approach":[98,164],"simplifies":[99],"process":[102],"replacing":[104],"complex":[105],"computations":[107],"with":[108],"lightweight":[109],"operations,":[111],"resulting":[112],"reduced":[114],"improved":[118],"scalability.":[119],"Experimental":[120],"results":[121],"demonstrate":[122],"effectiveness":[124],"achieving":[128],"competitive":[129],"accuracy":[130],"while":[134],"significantly":[135],"reducing":[136],"number":[138,155],"parameters.":[140],"The":[141],"transition":[142],"yields":[145],"reduction":[147],"two":[149],"orders":[150],"magnitude":[152],"compared":[158],"baseline":[160],"making":[162],"our":[163],"promising":[165],"deployment":[167],"resource-constrained":[169],"applications":[170],"such":[171],"edge":[173],"IoT":[176],"devices.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}