{"id":"https://openalex.org/W4392026285","doi":"https://doi.org/10.1109/aipr60534.2023.10440662","title":"The training accuracy of two-layer neural networks: its estimation and understanding using random datasets","display_name":"The training accuracy of two-layer neural networks: its estimation and understanding using random datasets","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4392026285","doi":"https://doi.org/10.1109/aipr60534.2023.10440662"},"language":"en","primary_location":{"id":"doi:10.1109/aipr60534.2023.10440662","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aipr60534.2023.10440662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","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/A5020362391","display_name":"Shuyue Guan","orcid":"https://orcid.org/0000-0002-3779-9368"},"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":true,"raw_author_name":"Shuyue Guan","raw_affiliation_strings":["The George Washington University,Department of Biomedical Engineering,Washington,DC,USA","Department of Biomedical Engineering, The George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"The George Washington University,Department of Biomedical Engineering,Washington,DC,USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Department of Biomedical Engineering, The George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071064016","display_name":"Murray H. Loew","orcid":"https://orcid.org/0000-0002-1255-9341"},"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":"Murray Loew","raw_affiliation_strings":["The George Washington University,Department of Biomedical Engineering,Washington,DC,USA","Department of Biomedical Engineering, The George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"The George Washington University,Department of Biomedical Engineering,Washington,DC,USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Department of Biomedical Engineering, The George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020362391"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20479356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"97","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9988999962806702,"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":0.9988999962806702,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9865999817848206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7522339224815369},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6461755037307739},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6444886922836304},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6057133674621582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5635979771614075},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5455403923988342},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4596090316772461},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4523620307445526},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4500772953033447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36548542976379395},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3237708806991577},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.053131043910980225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522339224815369},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6461755037307739},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6444886922836304},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6057133674621582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5635979771614075},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5455403923988342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4596090316772461},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4523620307445526},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4500772953033447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36548542976379395},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3237708806991577},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.053131043910980225},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aipr60534.2023.10440662","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aipr60534.2023.10440662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2025762001","https://openalex.org/W2945526235","https://openalex.org/W3041012898","https://openalex.org/W3126868393","https://openalex.org/W3180849877","https://openalex.org/W4302161581","https://openalex.org/W6604254268","https://openalex.org/W6658987400","https://openalex.org/W6732865767","https://openalex.org/W6752292159","https://openalex.org/W6754995021","https://openalex.org/W6756001544","https://openalex.org/W6758902322","https://openalex.org/W6762997939","https://openalex.org/W6770938554","https://openalex.org/W6780019567"],"related_works":["https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W230091440","https://openalex.org/W3171520305","https://openalex.org/W3135126032","https://openalex.org/W1924178503","https://openalex.org/W2233261550","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Although":[0],"the":[1,14,20,44,83,99,104,110,115,135,143,163,169,204],"neural":[2,50,89],"network":[3],"(NN)":[4],"technique":[5],"plays":[6],"a":[7,35,67,191,195],"vital":[8],"role":[9],"in":[10,114,128,184],"machine":[11],"learning,":[12],"understanding":[13,208],"mechanism":[15,164],"of":[16,22,101,106,112,157,165,171,207],"NN":[17,152,166],"models":[18,167],"and":[19,109,142],"transparency":[21],"deep":[23,209],"learning":[24],"still":[25],"require":[26],"more":[27],"basic":[28],"research.":[29],"In":[30],"this":[31,158],"study,":[32],"we":[33],"propose":[34],"novel":[36],"theory":[37,145],"based":[38],"on":[39,52,91,203],"space":[40],"partitioning":[41],"to":[42,59,69,149,161,177,200],"estimate":[43,70,150],"approximate":[45],"training":[46,71,84,126,173],"accuracy":[47,72,85,174],"for":[48,86,139,194,198],"two-layer":[49,87],"networks":[51,90],"random":[53,93],"datasets":[54,94],"without":[55,73],"training.":[56],"There":[57],"appear":[58],"be":[60],"no":[61],"other":[62],"studies":[63],"that":[64,134],"have":[65,120],"proposed":[66,144],"method":[68,81,123,136],"using":[74,95,124],"input":[75],"data":[76],"and/or":[77],"trained":[78],"models.":[79,153],"Our":[80],"estimates":[82],"fully-connected":[88],"two-class":[92],"only":[96],"three":[97],"arguments:":[98],"dimensionality":[100],"inputs":[102,107],"(d),":[103],"number":[105,111],"(N),":[108],"neurons":[113],"hidden":[116],"layer":[117],"(L).":[118],"We":[119],"verified":[121],"our":[122,129],"real":[125],"accuracies":[127],"experiments.":[130],"The":[131,154],"results":[132],"indicate":[133],"will":[137],"work":[138],"any":[140],"dimension,":[141],"could":[146],"also":[147],"extend":[148],"deeper":[151],"main":[155],"purpose":[156],"paper":[159],"is":[160],"understand":[162],"by":[168],"approach":[170],"estimating":[172],"but":[175],"not":[176],"analyze":[178],"their":[179,182],"generalization":[180],"nor":[181],"performance":[183],"real-world":[185],"applications.":[186],"This":[187],"study":[188],"may":[189],"provide":[190],"starting":[192],"point":[193],"new":[196],"way":[197],"researchers":[199],"make":[201],"progress":[202],"difficult":[205],"problem":[206],"learning.":[210]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}