{"id":"https://openalex.org/W7151286904","doi":"https://doi.org/10.1109/icmla66185.2025.00096","title":"Adaptive Kernel Selection: Performance Pattern Analysis Across Network Depth Hierarchies and Dataset Complexities","display_name":"Adaptive Kernel Selection: Performance Pattern Analysis Across Network Depth Hierarchies and Dataset Complexities","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151286904","doi":"https://doi.org/10.1109/icmla66185.2025.00096"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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/A5122586731","display_name":"Areen S. Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Areen Patil","raw_affiliation_strings":["University of Maryland, College Park,Department of Computer Science,College Park,United States"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park,Department of Computer Science,College Park,United States","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133135000","display_name":"Rehaan Kadhar","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rehaan Kadhar","raw_affiliation_strings":["University of California, Berkeley,Department of Aerospace Engineering,Berkeley,United States"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley,Department of Aerospace Engineering,Berkeley,United States","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122586731"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74900795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.18610000610351562,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10057","display_name":"Face and Expression Recognition","score":0.18610000610351562,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.1356000006198883,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.05130000039935112,"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/pattern-analysis","display_name":"Pattern analysis","score":0.5181000232696533},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42910000681877136},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.3467999994754791},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28060001134872437},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.2800000011920929},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.26159998774528503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5921000242233276},{"id":"https://openalex.org/C2985264313","wikidata":"https://www.wikidata.org/wiki/Q378859","display_name":"Pattern analysis","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5078999996185303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2776088427","wikidata":"https://www.wikidata.org/wiki/Q378859","display_name":"Pattern detection","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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":8,"referenced_works":["https://openalex.org/W2116360511","https://openalex.org/W2149194912","https://openalex.org/W2176287621","https://openalex.org/W2274405424","https://openalex.org/W2922509574","https://openalex.org/W2964184826","https://openalex.org/W3034421924","https://openalex.org/W3214897310"],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"rely":[4],"on":[5,113],"fixed-size":[6],"kernels":[7,135,148],"that":[8,27,129,164,192],"limit":[9],"their":[10],"ability":[11],"to":[12,86,186],"adaptively":[13],"capture":[14],"multi-scale":[15,171],"features.":[16],"This":[17,159],"paper":[18],"presents":[19],"a":[20,198],"novel":[21],"attention-based":[22,193],"dynamic":[23,61,188,194],"kernel":[24,45,58,92,161,195],"selection":[25,93,162,196],"architecture":[26],"enables":[28],"adaptive":[29,91,166],"feature":[30,140,172],"extraction":[31],"through":[32,60],"lightweight":[33],"channel-wise":[34],"attention":[35,55,126],"mechanisms.":[36],"Our":[37],"approach":[38],"employs":[39],"three":[40,75],"parallel":[41],"convolutional":[42],"branches":[43],"with":[44,64,118],"sizes":[46],"{3\u00d73,":[47],"5\u00d75,":[48],"7\u00d77}":[49],"combined":[50],"using":[51,81],"Global":[52],"Average":[53],"Pooling-based":[54],"weights,":[56],"achieving":[57,106],"adaptation":[59],"feature-level":[62],"aggregation":[63],"<":[65],"2%":[66],"parameter":[67,183],"overhead.":[68],"We":[69],"systematically":[70],"evaluate":[71],"our":[72],"method":[73],"across":[74],"benchmark":[76],"datasets":[77],"(Fashion-MNIST,":[78],"CIFAR-10,":[79],"CIFAR-100)":[80],"five":[82],"independent":[83],"random":[84],"seeds":[85],"ensure":[87],"statistical":[88,119],"validity.":[89],"The":[90,177],"mechanism":[94,167],"consistently":[95],"outperforms":[96],"standard":[97],"fixed-kernel":[98],"CNNs":[99],"in":[100],"7":[101],"out":[102],"of":[103,109,124],"9":[104],"configurations,":[105],"notable":[107],"improvements":[108,180],"1.82%":[110],"\u00b1":[111],"0.52%":[112],"CIFAR-10":[114],"(85.32%":[115],"vs":[116],"83.50%)":[117],"significance":[120],"(p<":[121],"0.05).":[122],"Analysis":[123],"learned":[125],"patterns":[127],"reveals":[128],"early":[130],"layers":[131,144],"preferentially":[132],"utilize":[133],"smaller":[134],"(3\u00d73:":[136],"~75-80%)":[137],"for":[138,151,201],"fine-grained":[139],"extraction,":[141],"while":[142,206],"deeper":[143],"increasingly":[145],"leverage":[146],"larger":[147],"(7\u00d77:":[149],"~70-85%)":[150],"global":[152],"contextual":[153],"integration,":[154],"mirroring":[155],"biological":[156],"vision":[157],"systems.":[158],"hierarchical":[160],"demonstrates":[163],"the":[165],"successfully":[168],"learns":[169],"meaningful":[170],"hierarchies":[173],"without":[174],"explicit":[175],"supervision.":[176],"consistent":[178],"performance":[179],"and":[181],"superior":[182],"efficiency":[184],"compared":[185],"existing":[187],"convolution":[189],"methods":[190],"indicate":[191],"represents":[197],"promising":[199],"direction":[200],"enhancing":[202],"CNN":[203],"representational":[204],"capacity":[205],"maintaining":[207],"computational":[208],"efficiency.":[209]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}