{"id":"https://openalex.org/W4320008771","doi":"https://doi.org/10.1109/jetcas.2023.3238295","title":"Device Modeling Bias in ReRAM-Based Neural Network Simulations","display_name":"Device Modeling Bias in ReRAM-Based Neural Network Simulations","publication_year":2023,"publication_date":"2023-01-20","ids":{"openalex":"https://openalex.org/W4320008771","doi":"https://doi.org/10.1109/jetcas.2023.3238295"},"language":"en","primary_location":{"id":"doi:10.1109/jetcas.2023.3238295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2023.3238295","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"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 Journal on Emerging and Selected Topics in Circuits and Systems","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/A5001880808","display_name":"Osama Yousuf","orcid":"https://orcid.org/0000-0002-7123-3982"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Osama Yousuf","raw_affiliation_strings":["Electrical and Computer Engineering Department, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0002-7123-3982","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065630488","display_name":"Imtiaz Hossen","orcid":"https://orcid.org/0000-0002-2931-0518"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imtiaz Hossen","raw_affiliation_strings":["Electrical and Computer Engineering Department, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0002-2931-0518","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008976251","display_name":"Matthew W. Daniels","orcid":"https://orcid.org/0000-0002-3390-4714"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew W. Daniels","raw_affiliation_strings":["National Institute of Standards and Technology, Gaithersburg, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-3390-4714","affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology, Gaithersburg, MD, USA","institution_ids":["https://openalex.org/I1321296531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043422237","display_name":"Martin Lueker-Boden","orcid":"https://orcid.org/0000-0002-4603-7023"},"institutions":[{"id":"https://openalex.org/I4210121352","display_name":"Western Digital (United States)","ror":"https://ror.org/02hqwnx33","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121352"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Lueker-Boden","raw_affiliation_strings":["Western Digital Technologies, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Western Digital Technologies, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210121352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058811779","display_name":"Andrew Dienstfrey","orcid":"https://orcid.org/0000-0002-5461-8741"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Dienstfrey","raw_affiliation_strings":["National Institute of Standards and Technology, Boulder, CO, USA"],"raw_orcid":"https://orcid.org/0000-0002-5461-8741","affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology, Boulder, CO, USA","institution_ids":["https://openalex.org/I1321296531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077532268","display_name":"Gina C. Adam","orcid":"https://orcid.org/0000-0003-0027-1145"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gina C. Adam","raw_affiliation_strings":["Electrical and Computer Engineering Department, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0003-0027-1145","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5807,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64234128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"13","issue":"1","first_page":"382","last_page":"394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"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/resistive-random-access-memory","display_name":"Resistive random-access memory","score":0.757766842842102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260987162590027},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.655998945236206},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6371480822563171},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5065509080886841},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46717625856399536},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.415763795375824},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.375776469707489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3494887351989746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3238011598587036},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16352394223213196},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12696877121925354},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1170969307422638}],"concepts":[{"id":"https://openalex.org/C182019814","wikidata":"https://www.wikidata.org/wiki/Q1143830","display_name":"Resistive random-access memory","level":3,"score":0.757766842842102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260987162590027},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.655998945236206},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6371480822563171},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5065509080886841},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46717625856399536},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.415763795375824},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.375776469707489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3494887351989746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3238011598587036},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16352394223213196},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12696877121925354},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1170969307422638},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jetcas.2023.3238295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2023.3238295","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"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 Journal on Emerging and Selected Topics in Circuits and Systems","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":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G7810178898","display_name":null,"funder_award_id":"ECNS21932N","funder_id":"https://openalex.org/F4320307793","funder_display_name":"Western Digital"},{"id":"https://openalex.org/G8687009354","display_name":"ALGORITHMIC DEVELOPMENT FOR HARDWARE AI COPROCESSORSPURPOSE: NEUROMORPHIC COMPUTATION REFERS TO A NON-VON-NEUMANN ARCHITECTURE INSPIRED BY THE STUDY OF BIOLOGICAL NERVOUS SYSTEMS. SUCH PROCESSORS HAVE GREAT PROMISE FOR ACCELERATING CERTAIN TYPES OF COMPUTATIONS WHILE REQUIRING SIGNIFICANTLY LESS POWER. AN IMPORTANT EXAMPLE IS MACHINE LEARNING, WHERE THE NEUROMORPHIC PROCESSOR CAN EFFICIENTLY IMPLEMENT A NEURAL NETWORK. TRAINING IS THE MOST ENERGY AND TIME INTENSIVE PART OF MACHINE LEARNING, AND SUCH TRAINING IS TYPICALLY DONE ON CONVENTIONAL COMPUTERS. THUS, HARDWARE THAT CAN TRAIN NEURAL NETWORKS EFFICIENTLY AND ACCURATELY IS SORELY NEEDED. THIS PROJECT AIMS TO ADDRESS THIS ISSUE BY PROVIDING A NEW APPROACH TO TRAIN THE MOST WELL-DEVELOPED TYPES OF NEW ARTIFICIAL INTELLIGENCE (AI) HARDWARE ACCELERATORS.ACTIVITIES TO BE PERFORMED: THE TEAM WILL DESIGN, CHARACTERIZE, AND TEST HARDWARE-AWARE DECOMPOSITION ALGORITHMS FOR COMPUTATIONS ON MATRIX MANIFOLDS, INCLUDING, BUT NOT LIMITED TO, SINGULAR VALUE DECOMPOSITION (SVD) AND NON-NEGATIVE MATRIX FACTORIZATION. SUCH COMPUTATIONS REPRESENT COMPUTE-INTENSIVE PARTS OF MANY AI ALGORITHMS.EXPECTED OUTCOMES: THIS PROJECT SEEKS TO DEVELOP EXTREMELY EFFICIENT HARDWARE-BASED COMPRESSION STRATEGIES FOR DATA ANALYSIS AND COMPUTATION. SUCCESS IN THIS PROJECT WOULD MAKE IT FEASIBLE TO CREATE AI SYSTEMS THAT CAN CONTINUE TO LEARN WHILE DEPLOYED. FURTHERMORE, SIMILAR COMPUTATIONS ARE REQUIRED FOR DYNAMICAL AND STREAMING SENSOR ENVIRONMENTS ARISING, FOR EXAMPLE, IN INTERNET OF THINGS APPLICATIONS. SUCCESS IN THIS PROJECT COULD OPEN NEW OPPORTUNITIES FOR SMART DEVICES IN THE FUTURE.INTENDED BENEFICIARIES:  THE PROPOSED ALGORITHMS AND ADVANCED HARDWARE COULD BENEFIT A WIDE RANGE OF INDUSTRIES INCLUDING DEVELOPERS OF RESOURCE-CONSTRAINED INTERNET OF THINGS APPLICATIONS, MEDICAL IMPLANTABLE DEVICES, AND EDGE-SENSOR COMMUNICATION SYSTEMS. THE PROJECT PROVIDES NIST WITH AN OPPORTUNITY TO INVESTIGATE HARDWARE/SOFTWARE CO-DESIGN FOR EMERGING AI HARDWARE. IT THEREBY CONTRIBUTES A RESEARCH COMPONENT TO THE NATIONAL PRIORITY CENTERED ON INVESTMENT IN US-BASED SEMICONDUCTOR MANUFACTURING. FINALLY, THIS WORK WILL ALSO PLAY A ROLE IN EDUCATING THE NEXT GENERATION OF COMPUTER SCIENTISTS THROUGH CUTTING EDGE RESEARCH EXPERIENCES.SUBRECIPIENT ACTIVITIES: THERE ARE NO PLANNED SUBAWARDS.","funder_award_id":"70NANB22H018","funder_id":"https://openalex.org/F4320332178","funder_display_name":"National Institute of Standards and Technology"}],"funders":[{"id":"https://openalex.org/F4320307793","display_name":"Western Digital","ror":"https://ror.org/02hqwnx33"},{"id":"https://openalex.org/F4320309515","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1937359183","https://openalex.org/W1997629593","https://openalex.org/W2007339694","https://openalex.org/W2008697864","https://openalex.org/W2041984721","https://openalex.org/W2051209243","https://openalex.org/W2125769353","https://openalex.org/W2307193480","https://openalex.org/W2530591187","https://openalex.org/W2535534962","https://openalex.org/W2607144874","https://openalex.org/W2740220207","https://openalex.org/W2750916325","https://openalex.org/W2774817518","https://openalex.org/W2782791387","https://openalex.org/W2891777323","https://openalex.org/W2905425616","https://openalex.org/W2949259459","https://openalex.org/W2949676527","https://openalex.org/W2950548534","https://openalex.org/W2960778947","https://openalex.org/W2969812992","https://openalex.org/W2973064692","https://openalex.org/W3001684375","https://openalex.org/W3006299183","https://openalex.org/W3009436876","https://openalex.org/W3015980402","https://openalex.org/W3037050967","https://openalex.org/W3045934648","https://openalex.org/W3082899001","https://openalex.org/W3094874291","https://openalex.org/W3104147253","https://openalex.org/W3125908175","https://openalex.org/W3176964228","https://openalex.org/W3205515946","https://openalex.org/W3215918518","https://openalex.org/W4223507763","https://openalex.org/W4254504754","https://openalex.org/W4281628293","https://openalex.org/W6638783484","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W1908107260","https://openalex.org/W1952005211","https://openalex.org/W2048582679","https://openalex.org/W2782226720"],"abstract_inverted_index":{"Emerging":[0],"technologies":[1],"based":[2,199],"on":[3,177,188,193,200],"resistive":[4],"switching":[5,215],"(ReRAM)":[6],"devices":[7,35,107,157],"promise":[8],"to":[9,65,85,103,120,182],"improve":[10],"the":[11,55,77,113,178,184,218,225],"speed":[12],"and":[13,38,69,134,150,166,213,249],"energy":[14],"efficiency":[15],"of":[16,57,73,79,115,128,211],"next":[17],"generation":[18],"machine":[19],"learning":[20],"accelerators,":[21],"but":[22],"further":[23],"research":[24],"is":[25,36,60,92,168],"required":[26],"for":[27,108,148,158,227],"achieving":[28],"commercial":[29],"maturity.":[30],"System-level":[31],"prototyping":[32],"with":[33,145,235],"emerging":[34,105],"costly,":[37],"algorithmic":[39],"investigations":[40,230],"require":[41],"hardware":[42,109,185],"neural":[43,80,250],"network":[44,81,205,251],"modeling":[45,58,88,90,131,243],"which":[46],"often":[47],"deviates":[48],"from":[49,154,203],"experimental":[50,151],"reality.":[51],"In":[52],"this":[53,67],"work,":[54],"concept":[56],"bias":[59,91,244],"proposed":[61,222],"as":[62,238,240],"a":[63,99,135,189,208],"way":[64],"quantify":[66],"deviation":[68],"support":[70],"reliable":[71],"evaluation":[72],"device":[74,87,122,162,179,197,219,233],"populations":[75],"in":[76,118,217,245],"context":[78],"algorithms.":[82],"While":[83],"applicable":[84],"other":[86],"techniques,":[89],"investigated":[93],"here":[94],"using":[95,142],"jump":[96,129],"tables":[97,117],"-":[98,139],"promising":[100],"physics-less":[101],"technique":[102],"model":[104],"memory":[106],"networks.":[110],"Questions":[111],"about":[112],"fidelity":[114],"these":[116,171],"relation":[119],"stochastic":[121],"behavior":[123],"are":[124,140,164],"answered.":[125],"Two":[126],"methods":[127],"table":[130],"\u2013":[132],"binning":[133,138,201],"novel":[136],"Optuna-optimized":[137],"explored":[141],"synthetic":[143],"data":[144,152],"known":[146],"distributions":[147],"benchmarking":[149],"obtained":[153],"TiOx":[155],"ReRAM":[156],"practical":[159],"testing.":[160],"Novel":[161],"metrics":[163,172],"proposed,":[165],"it":[167],"shown":[169],"that":[170,196],"can":[173],"present":[174],"crucial":[175],"insights":[176],"population":[180],"prior":[181],"training":[183],"network.":[186],"Results":[187],"multi-layer":[190],"perceptron":[191],"trained":[192],"MNIST":[194],"show":[195],"models":[198,234],"deviate":[202],"target":[204],"accuracy":[206],"at":[207],"low":[209],"number":[210],"points":[212],"high":[214],"noise":[216],"dataset.":[220],"The":[221],"approach":[223],"opens":[224],"possibility":[226],"device-algorithm":[228],"co-design":[229],"into":[231],"statistical":[232],"better":[236],"performance,":[237],"well":[239],"experimentally":[241],"verified":[242],"different":[246],"in-memory":[247],"computing":[248],"architectures.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}