{"id":"https://openalex.org/W4402352924","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649900","title":"QFALT: Quantization and Fault Aware Loss for Training Enables Performance Recovery with Unreliable Weights","display_name":"QFALT: Quantization and Fault Aware Loss for Training Enables Performance Recovery with Unreliable Weights","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352924","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649900"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10649900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10649900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5073551695","display_name":"Anmol Biswas","orcid":"https://orcid.org/0000-0002-2363-5864"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anmol Biswas","raw_affiliation_strings":["Indian Institute of Technology Bombay,Electrical Engineering Department,Mumbai,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Electrical Engineering Department,Mumbai,India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073593093","display_name":"Udayan Ganguly","orcid":"https://orcid.org/0000-0002-1498-5993"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Udayan Ganguly","raw_affiliation_strings":["Indian Institute of Technology Bombay,Electrical Engineering Department,Mumbai,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Electrical Engineering Department,Mumbai,India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073551695"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.7724,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76285831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9939000010490417,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9939000010490417,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9908999800682068,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9466000199317932,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.752678394317627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7445063591003418},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6562042236328125},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4185316562652588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3520810604095459},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.32584017515182495},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19072094559669495},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10276076197624207},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.058852583169937134}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.752678394317627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445063591003418},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6562042236328125},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4185316562652588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3520810604095459},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.32584017515182495},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19072094559669495},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10276076197624207},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.058852583169937134},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10649900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10649900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2194775991","https://openalex.org/W2560674852","https://openalex.org/W2735426554","https://openalex.org/W2750384547","https://openalex.org/W2894811292","https://openalex.org/W2945146780","https://openalex.org/W2964787841","https://openalex.org/W3097522836","https://openalex.org/W3118608800","https://openalex.org/W3203475348","https://openalex.org/W4248241425","https://openalex.org/W4288359573","https://openalex.org/W4297841771","https://openalex.org/W4312766536","https://openalex.org/W4385484769","https://openalex.org/W4385484800","https://openalex.org/W4385488643","https://openalex.org/W4394625834","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6743688258","https://openalex.org/W6762631276","https://openalex.org/W6763461347","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"is":[2,24,57,152],"the":[3,20,91,113,120,128,136,142],"dominant":[4],"method":[5,81],"for":[6,28,38,104,156,180],"classification":[7,102],"and":[8,60,86,94,106,164,177,182],"pattern":[9],"recognition":[10],"tasks.":[11],"Traditionally,":[12],"this":[13,67],"entails":[14],"running":[15],"large,":[16],"high-precision":[17],"models":[18,34,110],"on":[19,35,90],"cloud.":[21],"However,":[22],"there":[23],"an":[25],"increasing":[26],"demand":[27],"efficient,":[29],"lightweight":[30],"inference":[31],"using":[32],"compact":[33],"low-power":[36,181],"devices":[37],"edge":[39],"Artificial":[40],"Intelligence":[41],"(AI)":[42],"purposes.":[43],"This":[44,170],"necessitates":[45],"highly":[46],"quantized":[47,108],"models.":[48],"The":[49],"task":[50],"of":[51,122,144,160,167,174],"effectively":[52,153],"quantizing":[53],"a":[54,71,131,157],"deep-learning":[55],"model":[56],"not":[58],"trivial":[59],"many":[61],"approaches":[62],"have":[63],"been":[64],"proposed.":[65],"In":[66],"paper,":[68],"we":[69],"propose":[70],"regularization-based":[72],"technique":[73],"to":[74,112,126],"perform":[75],"quantization-aware":[76],"training.":[77],"We":[78,117],"validate":[79],"our":[80,123],"by":[82,141],"training":[83,179],"Fully":[84],"connected":[85],"Convolutional":[87],"Neural":[88],"Networks":[89],"Fashion-MNIST,":[92],"CIFAR-10,":[93],"CIFAR-100":[95],"datasets,":[96],"showing":[97],"under":[98],"1%":[99],"degradation":[100,137],"in":[101,130,138],"accuracy":[103],"2-bit":[105],"3-bit":[107],"weight":[109,149],"compared":[111],"32-bit":[114],"floating-point":[115],"baseline.":[116],"also":[118],"show":[119],"flexibility":[121],"regularization":[124],"function":[125],"train":[127],"network":[129],"fault-aware":[132],"manner,":[133],"such":[134],"that":[135],"performance":[139],"caused":[140],"presence":[143],"stuckat-0":[145],"faults":[146],"making":[147],"certain":[148],"states":[150],"unreachable":[151],"halved,":[154],"even":[155],"high":[158],"level":[159,166],"faulty":[161],"bits":[162],"(10%)":[163],"low":[165,183],"quantization":[168],"(3-bit).":[169],"opens":[171],"up":[172],"possibilities":[173],"improved":[175],"fault":[176],"variability-aware":[178],"bit-precision":[184],"neuromorphic":[185],"devices.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}