{"id":"https://openalex.org/W7140490541","doi":"https://doi.org/10.48550/arxiv.2603.24186","title":"TsetlinWiSARD: On-Chip Training of Weightless Neural Networks using Tsetlin Automata on FPGAs","display_name":"TsetlinWiSARD: On-Chip Training of Weightless Neural Networks using Tsetlin Automata on FPGAs","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140490541","doi":"https://doi.org/10.48550/arxiv.2603.24186"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.24186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102711915","display_name":"Shengyu Duan","orcid":"https://orcid.org/0009-0000-9321-8380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Shengyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121483551","display_name":"Marcos L. L. Sartori","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sartori, Marcos L. L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077777787","display_name":"Rishad Shafik","orcid":"https://orcid.org/0000-0001-5444-537X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shafik, Rishad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004061206","display_name":"A. Yakovlev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yakovlev, Alex","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5952000021934509,"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":0.5952000021934509,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.05959999933838844,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.034699998795986176,"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/overfitting","display_name":"Overfitting","score":0.7897999882698059},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.6317999958992004},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5569999814033508},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5544000267982483},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5249999761581421},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4973999857902527},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.44699999690055847}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7897999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674000263214111},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.6317999958992004},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354999899864197},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5115000009536743},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4584999978542328},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Increasing":[0],"demands":[1],"for":[2,15,95,109,138],"adaptability,":[3],"privacy,":[4],"and":[5,26,84,190],"security":[6],"at":[7],"the":[8,13,123,174],"edge":[9],"have":[10],"persistently":[11],"pushed":[12],"frontiers":[14],"a":[16,49,106,147],"new":[17],"generation":[18],"of":[19,125,178],"machine":[20],"learning":[21],"(ML)":[22],"algorithms":[23],"with":[24,129,173],"training":[25,107,128,153,170,198],"inference":[27],"capabilities":[28],"on-chip.":[29],"Weightless":[30],"Neural":[31],"Network":[32],"(WNN)":[33],"is":[34,39,146],"such":[35,55],"an":[36],"algorithm":[37],"that":[38,65,111,155],"principled":[40],"on":[41,68,75,97],"lookup":[42],"table":[43],"based":[44],"simple":[45],"neuron":[46],"structures.":[47],"As":[48],"result,":[50],"it":[51],"offers":[52],"architectural":[53],"benefits,":[54],"as":[56],"low-latency,":[57],"low-complexity":[58],"inference,":[59],"compared":[60,172,195],"to":[61,82,116,143,196],"deep":[62],"neural":[63],"networks":[64],"depend":[66],"heavily":[67],"multiply-accumulate":[69],"operations.":[70],"However,":[71],"traditional":[72,175],"WNNs":[73,110],"rely":[74],"memorization-based":[76],"one-shot":[77,127],"training,":[78],"which":[79],"either":[80],"leads":[81],"overfitting":[83,124],"reduced":[85,184],"accuracy":[86,158],"or":[87],"requires":[88],"tedious":[89],"post-training":[90],"adjustments,":[91],"limiting":[92],"their":[93],"effectiveness":[94],"efficient":[96,139],"chip":[98],"training.":[99,141],"In":[100],"this":[101],"work,":[102],"we":[103,181],"propose":[104],"TsetlinWiSARD,":[105],"approach":[108,145,165],"leverages":[112],"Tsetlin":[113],"Automata":[114],"(TAs)":[115],"enable":[117],"probabilistic,":[118],"feedback-driven":[119],"learning.":[120],"It":[121],"overcomes":[122],"WiSARD's":[126],"iterative":[130],"optimization,":[131],"while":[132,159],"maintaining":[133],"simple,":[134],"continuous":[135],"binary":[136],"feedback":[137],"on-chip":[140],"Central":[142],"our":[144],"field":[148],"programmable":[149],"gate":[150],"array":[151],"(FPGA)-based":[152],"architecture":[154],"delivers":[156],"state-of-the-art":[157],"significantly":[160],"improving":[161],"hardware":[162],"efficiency.":[163],"Our":[164],"provides":[166],"over":[167],"1000x":[168],"faster":[169],"when":[171],"WiSARD":[176],"implementation":[177],"WNNs.":[179],"Further,":[180],"demonstrate":[182],"22%":[183],"resource":[185],"usage,":[186],"93.3%":[187],"lower":[188,192],"latency,":[189],"64.2%":[191],"power":[193],"consumption":[194],"FPGA-based":[197],"accelerators":[199],"implementing":[200],"other":[201],"ML":[202],"algorithms.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-27T00:00:00"}