{"id":"https://openalex.org/W7125586149","doi":"https://doi.org/10.5281/zenodo.18362658","title":"Deep Differentiable Logic Gate Networks Based on Fuzzy Zadeh's T-norm","display_name":"Deep Differentiable Logic Gate Networks Based on Fuzzy Zadeh's T-norm","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W7125586149","doi":"https://doi.org/10.5281/zenodo.18362658"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.18362658","doi":"https://doi.org/10.5281/zenodo.18362658","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18362658","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18362658","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120090275","display_name":"Chan Duong Nguy","orcid":"https://orcid.org/0009-0006-1339-9841","observed_orcids":["https://orcid.org/0009-0006-1339-9841"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nguy, Chan Duong","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-1339-9841","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5120090275"],"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":0.6464999914169312,"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":0.6464999914169312,"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/T10320","display_name":"Neural Networks and Applications","score":0.19580000638961792,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.049800001084804535,"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/fuzzy-logic","display_name":"fuzzy logic","score":0.5220000147819519},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.5950000286102295},{"id":"https://openalex.org/keywords/sparse-neural-networks","display_name":"sparse neural networks","score":0.6880000233650208},{"id":"https://openalex.org/keywords/edge-devices","display_name":"edge devices","score":0.45399999618530273},{"id":"https://openalex.org/keywords/tabular-data-classification","display_name":"tabular data classification","score":0.7120000123977661},{"id":"https://openalex.org/keywords/bit-packing","display_name":"bit packing","score":0.5910000205039978},{"id":"https://openalex.org/keywords/ukasiewicz-t-norm","display_name":"\u0141ukasiewicz t-norm","score":0.9480000138282776}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8201000094413757},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7513999938964844},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.603600025177002},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.597100019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5708000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4788999855518341},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C187455244","wikidata":"https://www.wikidata.org/wiki/Q942353","display_name":"Boolean function","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4009000062942505},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C10418432","wikidata":"https://www.wikidata.org/wiki/Q560370","display_name":"AND gate","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2870999872684479},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.18362658","doi":"https://doi.org/10.5281/zenodo.18362658","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18362658","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"doi:10.5281/zenodo.18362659","doi":"https://doi.org/10.5281/zenodo.18362659","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18362659","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18362658","doi":"https://doi.org/10.5281/zenodo.18362658","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18362658","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133183521","https://openalex.org/W4415795242","https://openalex.org/W4415420813","https://openalex.org/W4417130444","https://openalex.org/W7214349352","https://openalex.org/W7221840560","https://openalex.org/W7214739037","https://openalex.org/W7168166526","https://openalex.org/W4416062403","https://openalex.org/W4414968560"],"abstract_inverted_index":{"Inference":[0],"efficiency":[1],"often":[2],"dictates":[3],"the":[4,38,59,109,224,236,239,253,264,318],"practicality":[5],"of":[6,44,54,69,147,218,226,266,272,293],"deep":[7],"learning":[8],"models":[9],"in":[10,19,275,306],"real":[11],"world":[12],"applications":[13],"especially":[14],"on":[15,82,151,177,322],"edge":[16],"devices":[17],"and":[18,72,87,114,144,164,170,188,216,245,288,300,315],"low":[20],"latency,":[21],"resource":[22],"constrained":[23],"scenarios,":[24],"yet":[25],"most":[26,124],"research":[27],"continues":[28],"to":[29,64,211,235,259],"emphasize":[30],"training":[31,68],"costs.":[32],"In":[33],"this":[34,307],"work,":[35],"we":[36,118],"revisit":[37],"differentiable":[39,276],"logic":[40,56,112,277,302],"gate":[41],"network":[42],"framework":[43],"Petersen":[45],"et":[46,158,182,193],"al.,":[47,159,183,194],"(2022),":[48],"which":[49],"uses":[50],"a":[51,96,105,152,227,269,311],"continuous":[52],"relaxation":[53,80],"discrete":[55],"operations":[57],"via":[58],"Menger":[60,237,254],"T-norm":[61,84,267],"(Menger,":[62],"1942)":[63],"enable":[65],"gradient":[66],"based":[67,81,131],"\u201dand\u201d,":[70],"\u201dxor\u201d,":[71],"other":[73,169],"Boolean":[74],"gates.":[75,127],"We":[76,161],"propose":[77],"an":[78],"alternative":[79,294],"Zadeh\u2019s":[83],"(Zadeh,":[85],"1965),":[86],"address":[88],"its":[89],"non-differentiability":[90],"at":[91,115,223,248,317],"equal":[92],"inputs":[93,141],"by":[94],"defining":[95],"consistent":[97],"backward":[98],"pass.":[99],"During":[100],"training,":[101],"each":[102,168],"neuron":[103],"learns":[104],"softmax":[106],"distribution":[107],"over":[108],"16":[110],"binary":[111],"gates":[113],"inference":[116,215],"time,":[117],"replace":[119],"these":[120],"distributions":[121],"with":[122],"their":[123],"likely":[125],"(hard)":[126],"The":[128,304],"resulting":[129],"Zadeh":[130,163,240],"networks":[132,166,176,208],"require":[133],"no":[134],"traditional":[135],"weights,":[136],"are":[137],"extremely":[138],"sparse":[139],"(two":[140],"per":[142,149],"neuron),":[143],"run":[145],"millions":[146],"inferences":[148],"second":[150],"single":[153],"CPU":[154],"(MINST":[155],"dataset":[156],"(LeCun":[157,181],"1998)).":[160],"benchmark":[162],"Menger-based":[165],"against":[167,171],"conventional":[172],"fully":[173],"connected":[174],"neural":[175],"tasks":[178],"including":[179],"MNIST":[180],"1998),":[184],"CIFAR-10":[185],"(Krizhevsky,":[186],"2012),":[187],"tabular":[189],"benchmarks":[190],"(MONK":[191],"(Thrun":[192],"1991),":[195],"Adult":[196],"(Becker":[197],"&":[198,204,328],"Kohavi,":[199],"1996),":[200],"Breast":[201],"Cancer":[202],"(Zwitter":[203],"Soklic,":[205],"1988)).":[206],"Zadeh-based":[207],"achieve":[209],"up":[210],"20":[212],"times":[213],"faster":[214,244],"orders":[217],"magnitude":[219],"lower":[220],"memory":[221],"use,":[222],"cost":[225],"modest":[228],"accuracy":[229],"gap":[230],"(1.8-9.5":[231],"percentage":[232],"points).":[233],"Compared":[234],"variant,":[238],"formulation":[241],"is":[242,256],"slightly":[243],"particularly":[246],"adept":[247],"isolating":[249],"singular":[250],"patterns,":[251],"while":[252],"variant":[255],"more":[257],"robust":[258],"noise.":[260],"Our":[261],"work":[262],"introduces":[263],"choice":[265],"as":[268,284],"new":[270],"axis":[271],"architectural":[273],"optimization":[274],"networks,":[278],"highlights":[279],"hardware":[280],"aware":[281],"considerations":[282],"such":[283],"bit":[285],"packing":[286],"strategies,":[287],"points":[289],"toward":[290],"future":[291],"exploration":[292],"fuzzy":[295],"relaxations":[296],"(e.g.,":[297],"\u0141ukasiewicz":[298],"T-norm)":[299],"hybrid":[301],"architectures.":[303],"results":[305],"thesis":[308],"were":[309],"from":[310],"peer-reviewed":[312],"paper":[313],"accepted":[314],"presented":[316],"6th":[319],"Polish":[320],"Conference":[321],"Artificial":[323],"Intelligence":[324],"PP-RAI":[325],"2025":[326],"(Wasilewski":[327],"Nguy,":[329],"2025).":[330]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-25T00:00:00"}