{"id":"https://openalex.org/W7127637350","doi":"https://doi.org/10.1109/tc.2026.3661114","title":"Efficient Memristor Neural Networks for Edge AI: On-Chip Learning, Noise Robustness, Device-Variation Tolerance, and Sublinear Energy and Time Scaling","display_name":"Efficient Memristor Neural Networks for Edge AI: On-Chip Learning, Noise Robustness, Device-Variation Tolerance, and Sublinear Energy and Time Scaling","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7127637350","doi":"https://doi.org/10.1109/tc.2026.3661114"},"language":null,"primary_location":{"id":"doi:10.1109/tc.2026.3661114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2026.3661114","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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/A5125096585","display_name":"M.Reza Eslami","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Reza Eslami","raw_affiliation_strings":["Electrical &#x0026; Computer Engineering Department, Clemson University (CU), Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0001-7532-8690","affiliations":[{"raw_affiliation_string":"Electrical &#x0026; Computer Engineering Department, Clemson University (CU), Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076527617","display_name":"Dhiman Biswas","orcid":null},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhiman Biswas","raw_affiliation_strings":["Physics and Astronomy Department, The University of Oklahoma, Norman, OK, USA"],"raw_orcid":"https://orcid.org/0009-0008-7272-2770","affiliations":[{"raw_affiliation_string":"Physics and Astronomy Department, The University of Oklahoma, Norman, OK, USA","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067576769","display_name":"Soheib Takhtardeshir","orcid":"https://orcid.org/0009-0008-5477-0920"},"institutions":[{"id":"https://openalex.org/I56475706","display_name":"Mid Sweden University","ror":"https://ror.org/019k1pd13","country_code":"SE","type":"education","lineage":["https://openalex.org/I56475706"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Soheib Takhtardeshir","raw_affiliation_strings":["Computer and Electrical Engineering Department, Mid Sweden University, Sundsvall, SE, Sweden"],"raw_orcid":"https://orcid.org/0009-0008-5477-0920","affiliations":[{"raw_affiliation_string":"Computer and Electrical Engineering Department, Mid Sweden University, Sundsvall, SE, Sweden","institution_ids":["https://openalex.org/I56475706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033454223","display_name":"Safura Sharifi","orcid":"https://orcid.org/0000-0002-4667-6650"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah S. Sharif","raw_affiliation_strings":["School of Electrical and Computer Engineering, The University of Oklahoma, Norman, OK, USA"],"raw_orcid":"https://orcid.org/0000-0002-4667-6650","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, The University of Oklahoma, Norman, OK, USA","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124992024","display_name":"Yaser M. Banad","orcid":null},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaser M. Banad","raw_affiliation_strings":["School of Electrical and Computer Engineering, The University of Oklahoma, Norman, OK, USA"],"raw_orcid":"https://orcid.org/0000-0001-7339-810X","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, The University of Oklahoma, Norman, OK, USA","institution_ids":["https://openalex.org/I8692664"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5125096585"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2398864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":"5","first_page":"1723","last_page":"1736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9879000186920166,"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":0.9879000186920166,"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":0.0032999999821186066,"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/T11128","display_name":"Transition Metal Oxide Nanomaterials","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/2507","display_name":"Polymers and Plastics"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/memristor","display_name":"Memristor","score":0.8183000087738037},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6574000120162964},{"id":"https://openalex.org/keywords/neuromorphic-engineering","display_name":"Neuromorphic engineering","score":0.5601000189781189},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5527999997138977},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.501800000667572},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47609999775886536},{"id":"https://openalex.org/keywords/resistive-random-access-memory","display_name":"Resistive random-access memory","score":0.4447999894618988},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41839998960494995}],"concepts":[{"id":"https://openalex.org/C150072547","wikidata":"https://www.wikidata.org/wiki/Q212923","display_name":"Memristor","level":2,"score":0.8183000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730400025844574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.5601000189781189},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5527999997138977},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.501800000667572},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C182019814","wikidata":"https://www.wikidata.org/wiki/Q1143830","display_name":"Resistive random-access memory","level":3,"score":0.4447999894618988},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4004000127315521},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.39469999074935913},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.2653999924659729},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2026.3661114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2026.3661114","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5633974075317383}],"awards":[{"id":"https://openalex.org/G1381401746","display_name":null,"funder_award_id":"2432082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Memristor-based":[0],"neural":[1,191],"networks":[2],"promise":[3],"low-power,":[4],"high-density":[5],"neuromorphic":[6],"hardware,":[7],"yet":[8],"most":[9,105],"studies":[10],"remain":[11],"proof-of-concept":[12],"with":[13,78,157],"small":[14],"inputs":[15,53],"and":[16,37,43,58,97,113,154,182,188],"qualitative":[17,170],"reporting.":[18],"We":[19,92,120],"present":[20],"a":[21,28,47],"comprehensive":[22],"investigation":[23],"of":[24,143],"on-chip":[25],"learning":[26],"in":[27],"scalable":[29],"memristor":[30,190],"network,":[31],"modeling":[32],"realistic":[33],"non-idealities":[34],"including":[35],"device-to-device":[36],"cycle-to-cycle":[38],"variability,":[39],"conductance":[40],"programming":[41],"errors,":[42],"input":[44,127,158],"noise.":[45],"Using":[46],"30-memristor":[48],"architecture,":[49],"we":[50],"systematically":[51],"scale":[52],"from":[54,134],"3\u00d73":[55,118],"to":[56,75],"11x11":[57],"evaluate":[59],"classification":[60,125],"robustness":[61],"under":[62],"noisy":[63,80],"conditions.":[64],"Results":[65],"show":[66],"that":[67,168],"moderate":[68],"training":[69,95,111,115,144,149,183],"noise":[70,179],"improves":[71],"tolerance,":[72],"enabling":[73],"up":[74],"99%":[76],"accuracy":[77],"20%":[79],"tests,":[81],"whereas":[82],"aggressive":[83],"weight":[84],"quantization":[85],"at":[86],"higher":[87],"resolutions":[88],"can":[89],"degrade":[90],"accuracy.":[91],"quantify":[93],"average":[94,110],"time":[96,112,145],"energy":[98,116,123,150],"across":[99],"device":[100],"types;":[101],"chromium":[102],"devices":[103],"are":[104],"efficient,":[106],"achieving":[107],"2.4":[108],"s":[109],"18.9mJ":[114],"for":[117,162,199],"tasks.":[119],"also":[121],"report":[122],"per":[124],"versus":[126],"size,":[128],"establishing":[129],"concrete":[130],"benchmarks":[131],"often":[132],"absent":[133],"prior":[135],"work.":[136],"A":[137],"Big-O":[138],"analysis":[139],"indicates":[140],"sub-linear":[141],"growth":[142],"(n<sup":[146,151],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[147,152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0.26</sup>),":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0.28</sup>),":[153],"inference":[155],"cost":[156],"dimension,":[159],"supporting":[160],"suitability":[161],"edge":[163,201],"deployment.":[164],"Unlike":[165],"earlier":[166],"demonstrations":[167],"emphasized":[169],"recognition,":[171],"this":[172],"study":[173],"provides":[174],"quantitative":[175],"trade-offs":[176],"among":[177],"accuracy,":[178],"robustness,":[180],"energy,":[181],"time,":[184],"bridging":[185],"device-level":[186],"feasibility":[187],"practical":[189],"network":[192],"accelerators.":[193],"These":[194],"results":[195],"guide":[196],"design":[197],"choices":[198],"deployable":[200],"systems.":[202]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-02-06T00:00:00"}