{"id":"https://openalex.org/W4414857723","doi":"https://doi.org/10.1016/j.neucom.2026.133905","title":"Optimal density functions for weighted convolution in learning models","display_name":"Optimal density functions for weighted convolution in learning models","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W4414857723","doi":"https://doi.org/10.1016/j.neucom.2026.133905"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133905","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133905","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2026.133905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077319872","display_name":"Simone Cammarasana","orcid":"https://orcid.org/0000-0002-2549-8330"},"institutions":[{"id":"https://openalex.org/I4210146308","display_name":"Institute of Intelligent Systems for Automation","ror":"https://ror.org/051t1q308","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210146308","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Simone Cammarasana","raw_affiliation_strings":["CNR IMATI, Via de Marini 6, Genova, 16149, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2549-8330","affiliations":[{"raw_affiliation_string":"CNR IMATI, Via de Marini 6, Genova, 16149, Italy","institution_ids":["https://openalex.org/I4210146308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079829556","display_name":"Giuseppe Patan\u00e8","orcid":"https://orcid.org/0000-0002-2276-9553"},"institutions":[{"id":"https://openalex.org/I4210146308","display_name":"Institute of Intelligent Systems for Automation","ror":"https://ror.org/051t1q308","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210146308","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Patan\u00e8","raw_affiliation_strings":["CNR IMATI, Via de Marini 6, Genova, 16149, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2276-9553","affiliations":[{"raw_affiliation_string":"CNR IMATI, Via de Marini 6, Genova, 16149, Italy","institution_ids":["https://openalex.org/I4210146308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077319872"],"corresponding_institution_ids":["https://openalex.org/I4210146308"],"apc_list":{"value":2670,"currency":"USD","value_usd":2670},"apc_paid":{"value":2670,"currency":"USD","value_usd":2670},"fwci":7.0482,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.930186,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"693","issue":null,"first_page":"133905","last_page":"133905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9406999945640564,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9406999945640564,"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/convolution","display_name":"Convolution (computer science)","score":0.7134000062942505},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5906999707221985},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5541999936103821},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5284000039100647},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4715999960899353},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.4302999973297119},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39309999346733093}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7134000062942505},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5541999936103821},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5406000018119812},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5254999995231628},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4226999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4034999907016754},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C134466208","wikidata":"https://www.wikidata.org/wiki/Q1520657","display_name":"Weight function","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C86254553","wikidata":"https://www.wikidata.org/wiki/Q5166605","display_name":"Convolution power","level":5,"score":0.2653000056743622},{"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/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C195699287","wikidata":"https://www.wikidata.org/wiki/Q7915722","display_name":"Variable kernel density estimation","level":4,"score":0.2547999918460846}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.neucom.2026.133905","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133905","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.24527","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.24527","pdf_url":"https://arxiv.org/pdf/2505.24527","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.24527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.24527","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2026.133905","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133905","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,86,105],"paper":[1],"proposes":[2],"a":[3,17,49,59,116,173,226],"novel":[4],"weighted":[5,71,143,170,222,248],"convolution":[6,72,144,171,223,249],"for":[7,135],"signals":[8],"defined":[9],"on":[10,131,196,201],"regular":[11],"grids":[12],"(2D":[13],"images)":[14],"by":[15,57,195,200],"optimising":[16],"density":[18,56,64,88,123,227,235],"function":[19,65,228,236],"that":[20,141,224],"scales":[21],"the":[22,32,39,54,63,67,70,79,90,93,96,102,108,111,122,126,142,147,155,158,165,169,179,183,186,214,241],"contribution":[23],"of":[24,81,92,95,110,157,175,182,213,243],"neighbouring":[25,45],"pixels":[26,46],"according":[27],"to":[28,75,77,101,150,178,229,239],"their":[29],"distance":[30],"from":[31,38,121],"central":[33],"pixel.":[34],"This":[35],"choice":[36],"differs":[37],"uniform":[40,103],"convolution,":[41],"which":[42],"treats":[43],"all":[44],"equally.":[47],"Given":[48],"convolutional":[50,112],"network,":[51],"we":[52],"compute":[53],"optimal":[55,87,221],"minimising":[58],"loss":[60],"functional,":[61],"with":[62,99,161,168,185],"as":[66],"variable.":[68],"Then,":[69],"is":[73,208,237],"applied":[74],"CNNs":[76],"improve":[78],"accuracy":[80,242],"image-processing":[82],"tasks":[83],"(denoising,":[84],"classification).":[85],"improves":[89,146,250],"convergence":[91],"weights":[94,114],"learning":[97,133,215,244],"model":[98,167,184],"respect":[100],"density.":[104],"framework":[106],"separates":[107],"optimisation":[109,124],"kernel":[113],"(using":[115,125],"stochastic":[117],"gradient":[118],"descent":[119],"method)":[120],"DIRECT-L":[127],"algorithm).":[128],"Experimental":[129],"tests":[130],"SOTA":[132],"models":[134],"image":[136,251],"denoising":[137,156,252],"and":[138,199,253],"classification":[139,254],"show":[140],"significantly":[145],"performance":[148],"compared":[149,177],"standard":[151,187,197],"convolution.":[152,188],"For":[153],"example,":[154],"DIV2K":[159],"dataset":[160],"Gaussian":[162],"noise":[163],"through":[164],"DnCNN":[166],"reaches":[172],"PSNR":[174],"31.02,":[176],"29.09":[180],"value":[181],"While":[189],"our":[190],"method":[191],"increases":[192],"execution":[193],"time":[194],"hardware":[198],"GPU":[202],"in":[203],"modern":[204],"HPC":[205],"environments,":[206],"it":[207],"robust":[209],"across":[210],"several":[211],"hyperparameters":[212],"model.":[216],"\u2022":[217,233,246],"We":[218],"introduce":[219],"an":[220],"applies":[225],"scale":[230],"pixel":[231],"contribution.":[232],"A":[234],"optimised":[238],"increase":[240],"models.":[245],"Optimal":[247],"problems.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}