{"id":"https://openalex.org/W3159127181","doi":"https://doi.org/10.1109/iscas51556.2021.9401075","title":"Best Practices for Designing and Training Neural Networks Subjected to Random Variations","display_name":"Best Practices for Designing and Training Neural Networks Subjected to Random Variations","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3159127181","doi":"https://doi.org/10.1109/iscas51556.2021.9401075","mag":"3159127181"},"language":"en","primary_location":{"id":"doi:10.1109/iscas51556.2021.9401075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5000307898","display_name":"Devon Janke","orcid":"https://orcid.org/0000-0002-7983-0896"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Devon Janke","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033437141","display_name":"David V. Anderson","orcid":"https://orcid.org/0000-0002-8571-4613"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David V. Anderson","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000307898"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61272806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"27","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":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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/T10558","display_name":"Advancements in Semiconductor Devices and Circuit Design","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9712662696838379},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7730385065078735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7571680545806885},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6532595157623291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.601695716381073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5442027449607849},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5257285833358765},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.494050532579422},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3759344518184662}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9712662696838379},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7730385065078735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571680545806885},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6532595157623291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.601695716381073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5442027449607849},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5257285833358765},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.494050532579422},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3759344518184662},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas51556.2021.9401075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1489770478","https://openalex.org/W1594260290","https://openalex.org/W2025961527","https://openalex.org/W2061180981","https://openalex.org/W2094909694","https://openalex.org/W2097566223","https://openalex.org/W2127026245","https://openalex.org/W2131525166","https://openalex.org/W2143165843","https://openalex.org/W2151484507","https://openalex.org/W2463240802","https://openalex.org/W2517138139","https://openalex.org/W2528655371","https://openalex.org/W2725092576","https://openalex.org/W2766749946","https://openalex.org/W2800923122","https://openalex.org/W2809230488","https://openalex.org/W2907560147","https://openalex.org/W2912910336","https://openalex.org/W2943010653","https://openalex.org/W2953146400","https://openalex.org/W2991698235","https://openalex.org/W3042184340","https://openalex.org/W3083350380","https://openalex.org/W3163464523","https://openalex.org/W3170402172","https://openalex.org/W4239089090","https://openalex.org/W4251370906","https://openalex.org/W4255059847","https://openalex.org/W4313730896","https://openalex.org/W6629296980","https://openalex.org/W6674300382","https://openalex.org/W6719230046","https://openalex.org/W6782481672"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"When":[0,28],"a":[1,11,55,78,102],"neural":[2,56,95],"network":[3,65],"is":[4,16,35,106],"trained":[5],"and":[6,72,99,101],"used":[7],"for":[8,43,81],"inference":[9],"in":[10,30,74,85,94],"digital":[12],"hardware":[13],"architecture,":[14],"it":[15],"normally":[17],"expected":[18],"that":[19,111],"the":[20,45,51,61,64,68,83],"performance":[21,53],"will":[22],"translate":[23],"exactly":[24],"to":[25,91,108],"new":[26],"hardware.":[27],"implemented":[29],"low-power":[31],"analog":[32],"systems,":[33],"there":[34],"no":[36],"such":[37],"luxury.":[38],"This":[39],"paper":[40],"explores":[41],"methods":[42,110],"reducing":[44],"impact":[46],"of":[47,54,60,63,70,89],"inter-device":[48],"variations":[49],"on":[50],"final":[52],"network.":[57],"An":[58],"analysis":[59],"effect":[62],"shape,":[66],"including":[67],"number":[69,88],"layers":[71],"neurons":[73],"each":[75],"layer,":[76],"reveals":[77],"general":[79],"pattern":[80],"minimizing":[82],"variability":[84],"accuracy.":[86],"A":[87],"means":[90],"reduce":[92],"overfitting":[93],"networks":[96],"are":[97],"discussed":[98],"compared,":[100],"more":[103],"thorough":[104],"demonstration":[105],"given":[107],"training":[109],"mitigate":[112],"device":[113],"overfitting.":[114]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}