{"id":"https://openalex.org/W4414499786","doi":"https://doi.org/10.1109/aicas64808.2025.11173140","title":"Drift-Aware Regularization for Long-Term Stability in Phase-Change Memory Based Neural Network Implementations","display_name":"Drift-Aware Regularization for Long-Term Stability in Phase-Change Memory Based Neural Network Implementations","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4414499786","doi":"https://doi.org/10.1109/aicas64808.2025.11173140"},"language":"en","primary_location":{"id":"doi:10.1109/aicas64808.2025.11173140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5106513198","display_name":"Adnan Haidar","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adnan Haidar","raw_affiliation_strings":["Technische Universität,Faculty of Electrical and Computer Engineering,Dresden,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität,Faculty of Electrical and Computer Engineering,Dresden,Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088436387","display_name":"Vasileios Ntinas","orcid":"https://orcid.org/0000-0002-2367-5567"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vasileios Ntinas","raw_affiliation_strings":["Technische Universität,Faculty of Electrical and Computer Engineering,Dresden,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität,Faculty of Electrical and Computer Engineering,Dresden,Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012451668","display_name":"Ronald Tetzlaff","orcid":"https://orcid.org/0000-0001-7436-0103"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ronald Tetzlaff","raw_affiliation_strings":["Technische Universität,Faculty of Electrical and Computer Engineering,Dresden,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität,Faculty of Electrical and Computer Engineering,Dresden,Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9947999715805054,"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/T10320","display_name":"Neural Networks and Applications","score":0.9947999715805054,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9771999716758728,"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/T11315","display_name":"Phase-change materials and chalcogenides","score":0.9527000188827515,"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/mnist-database","display_name":"MNIST database","score":0.7208999991416931},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6452000141143799},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6274999976158142},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6259999871253967},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5347999930381775},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5202999711036682},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.478300005197525},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7208999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656499981880188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6452000141143799},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6259999871253967},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5202999711036682},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.42500001192092896},{"id":"https://openalex.org/C6899612","wikidata":"https://www.wikidata.org/wiki/Q852911","display_name":"Resistive touchscreen","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38580000400543213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C182019814","wikidata":"https://www.wikidata.org/wiki/Q1143830","display_name":"Resistive random-access memory","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas64808.2025.11173140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1937359183","https://openalex.org/W2294387582","https://openalex.org/W2560615381","https://openalex.org/W2769049661","https://openalex.org/W2796625795","https://openalex.org/W2805362231","https://openalex.org/W2807750997","https://openalex.org/W2889448077","https://openalex.org/W2948661249","https://openalex.org/W2963387357","https://openalex.org/W2963587345","https://openalex.org/W3003151806","https://openalex.org/W3005874416","https://openalex.org/W3176606713","https://openalex.org/W3195461290","https://openalex.org/W3201969459","https://openalex.org/W4226225603","https://openalex.org/W4320015730","https://openalex.org/W4386293192","https://openalex.org/W4389082012","https://openalex.org/W4400233540"],"related_works":[],"abstract_inverted_index":{"Phase-Change":[0],"Memory":[1],"(PCM)":[2],"based":[3],"resistive":[4],"crossbars":[5],"are":[6],"a":[7,22,33,48,89,108,151],"promising":[8],"technology":[9],"for":[10,35,112,155],"energy-efficient":[11,153],"neural":[12,145],"network":[13],"inference":[14,80,156],"in":[15,25,82,138,157],"analog":[16],"in-memory":[17],"computing":[18],"(AIMC)":[19],"systems.":[20],"However,":[21],"conductance":[23,86],"drift":[24,55,91,120],"PCM":[26],"devices":[27],"degrades":[28],"performance":[29,81],"over":[30],"time,":[31],"posing":[32],"challenge":[34],"applications":[36],"requiring":[37],"long-term":[38],"stability.":[39],"In":[40,88],"order":[41],"to":[42,63,98,101,127],"overcome":[43],"such":[44],"problems,":[45],"we":[46],"propose":[47],"drift-aware":[49,136],"regularization":[50,137],"framework":[51],"that":[52],"stabilizes":[53],"weight":[54],"during":[56],"training,":[57],"complemented":[58],"by":[59],"an":[60],"attention-based":[61],"mechanism":[62],"prioritize":[64],"critical":[65],"features.":[66],"Our":[67],"approach":[68],"significantly":[69],"improves":[70],"upon":[71],"traditional":[72],"hardware-aware":[73],"(HWA)":[74],"training":[75,106],"and":[76,142],"achieves":[77],"more":[78],"robust":[79],"the":[83,113,122,132,140],"presence":[84],"of":[85,134,144],"drift.":[87],"five-year":[90],"simulation,":[92],"our":[93,135],"method":[94],"reduces":[95],"classification":[96],"error":[97,123],"3.75%,":[99],"compared":[100],"9.14%":[102],"with":[103,118],"standard":[104],"HWA":[105],"on":[107,147],"benchmark":[109],"two-layer":[110],"perceptron":[111],"MNIST":[114],"dataset.":[115],"When":[116],"combined":[117],"global":[119],"compensation,":[121],"is":[124],"further":[125],"reduced":[126],"2.12%.":[128],"These":[129],"results":[130],"demonstrate":[131],"effectiveness":[133],"enhancing":[139],"stability":[141],"accuracy":[143],"networks":[146],"AIMC":[148],"hardware,":[149],"offering":[150],"scalable,":[152],"solution":[154],"resource-constrained":[158],"environments.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}