{"id":"https://openalex.org/W4417438652","doi":"https://doi.org/10.1109/tetci.2025.3641703","title":"Comparative Analysis of Inference Performance of Pre-Trained Convolutional Neural Networks in Analog Accelerators","display_name":"Comparative Analysis of Inference Performance of Pre-Trained Convolutional Neural Networks in Analog Accelerators","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W4417438652","doi":"https://doi.org/10.1109/tetci.2025.3641703"},"language":null,"primary_location":{"id":"doi:10.1109/tetci.2025.3641703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3641703","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-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/A5100876112","display_name":"Mafizur Rahman","orcid":"https://orcid.org/0009-0007-4870-0232"},"institutions":[{"id":"https://openalex.org/I250520410","display_name":"Prairie View A&M University","ror":"https://ror.org/0449kf092","country_code":"US","type":"education","lineage":["https://openalex.org/I250520410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mafizur Rahman","raw_affiliation_strings":["Department of Electrical and Computer Engineering, CREDIT Center, Prairie View A&M University, Prairie View, TX, USA"],"raw_orcid":"https://orcid.org/0009-0007-4870-0232","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, CREDIT Center, Prairie View A&M University, Prairie View, TX, USA","institution_ids":["https://openalex.org/I250520410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085031765","display_name":"Lijun Qian","orcid":"https://orcid.org/0000-0003-1577-3359"},"institutions":[{"id":"https://openalex.org/I250520410","display_name":"Prairie View A&M University","ror":"https://ror.org/0449kf092","country_code":"US","type":"education","lineage":["https://openalex.org/I250520410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lijun Qian","raw_affiliation_strings":["Department of Electrical and Computer Engineering, CREDIT Center, Prairie View A&M University, Prairie View, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1577-3359","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, CREDIT Center, Prairie View A&M University, Prairie View, TX, USA","institution_ids":["https://openalex.org/I250520410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100876112"],"corresponding_institution_ids":["https://openalex.org/I250520410"],"apc_list":null,"apc_paid":null,"fwci":0.6531,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7745126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":"2","first_page":"1324","last_page":"1339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9742000102996826,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9742000102996826,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.009100000374019146,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.006800000090152025,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7282999753952026},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6898000240325928},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6270999908447266},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5009999871253967},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4302000105381012},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41929998993873596},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4074999988079071},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202000260353088},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7282999753952026},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6898000240325928},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483999848365784},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5037000179290771},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4302000105381012},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.376800000667572},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.37139999866485596},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C6899612","wikidata":"https://www.wikidata.org/wiki/Q852911","display_name":"Resistive touchscreen","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2025.3641703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3641703","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3269630641","display_name":null,"funder_award_id":"W911NF-23-1-0214","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G3294896131","display_name":null,"funder_award_id":"W911NF-24-2-0133","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Resistive":[0],"crossbars":[1],"using":[2,62,76,112],"non-volatile":[3],"memory":[4],"devices":[5],"have":[6],"become":[7],"promising":[8],"components":[9],"for":[10,53,203,233,237],"implementing":[11],"deep":[12,176],"learning":[13],"models":[14,106],"in":[15,140,163],"hardware.":[16,210],"However,":[17],"crossbar-based":[18],"computations":[19],"encounter":[20],"a":[21],"notable":[22],"challenge":[23],"due":[24,173],"to":[25,89,131,135,174],"device":[26],"and":[27,43,45,59,97,138,191,218],"circuit-level":[28],"non-idealities.":[29],"In":[30],"this":[31,71],"study,":[32],"we":[33,122,179,240],"explore":[34,180],"three":[35,78,85,129,167,184],"recent":[36],"crossbar":[37],"simulation":[38,79],"tools,":[39],"namely,":[40],"AIHWKIT,":[41],"CrossSim,":[42],"MemTorch,":[44],"evaluate":[46,90,123],"four":[47,105],"pre-trained":[48],"convolutional":[49],"neural":[50],"networks":[51],"(CNNs)":[52],"image":[54],"classification":[55],"on":[56,127,194,209],"CIFAR-100,":[57],"MNIST,":[58],"SVHN":[60],"datasets":[61],"these":[63],"tools.":[64],"To":[65],"the":[66,73,102,128,141,181,204],"best":[67],"of":[68,81,104,115,166,183,207,245],"our":[69],"knowledge,":[70],"is":[72,225],"first":[74,100],"study":[75],"all":[77,148],"tools":[80,130],"analog":[82,95,136],"accelerators,":[83],"representing":[84],"distinctive":[86],"hardware":[87,142,171,199],"settings,":[88],"CNN-based":[91],"model":[92],"robustness":[93,103],"under":[94],"noise":[96,118,137],"nonlinearities.":[98],"We":[99],"test":[101],"(VGG19,":[107],"InceptionV3,":[108],"ResNet50,":[109],"&":[110],"MobilenetV2)":[111],"different":[113],"levels":[114],"white":[116],"Gaussian":[117],"as":[119,153,159],"baselines.":[120],"Then":[121],"their":[124,133],"inference":[125],"performance":[126,151,196],"determine":[132],"resilience":[134],"nonlinearities":[139],"environment.":[143],"Results":[144],"show":[145],"that":[146,214,228],"while":[147,236],"CNNs'":[149,222],"suffer":[150],"degradation":[152],"expected,":[154],"insights":[155],"are":[156,231],"obtained":[157],"such":[158],"ResNet50":[160],"outperforms":[161],"others":[162],"two":[164],"out":[165],"simulators":[168],"despite":[169],"real-world":[170],"imperfections":[172],"its":[175],"structure.":[177],"Furthermore,":[178],"impact":[182],"key":[185],"factors:":[186],"cell":[187,216],"bits,":[188],"ADC":[189,219],"resolution,":[190],"tile":[192],"size":[193],"CNN":[195,208],"across":[197],"various":[198],"configurations,":[200],"providing":[201],"recommendations":[202],"efficient":[205],"deployment":[206],"Our":[211],"results":[212],"suggest":[213],"increasing":[215],"bits":[217],"resolution":[220],"improves":[221],"performance.":[223],"It":[224],"also":[226],"observed":[227],"smaller":[229],"tiles":[230],"suitable":[232],"lightweight":[234],"models,":[235],"complex":[238],"networks,":[239],"should":[241],"choose":[242],"larger":[243],"shape":[244],"tiles.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-17T00:00:00"}