{"id":"https://openalex.org/W7161173413","doi":"https://doi.org/10.1016/j.neucom.2026.133948","title":"Prior-informed initialization of function-parameterizing networks: A spectral approach for Bag-of-Functions architectures","display_name":"Prior-informed initialization of function-parameterizing networks: A spectral approach for Bag-of-Functions architectures","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161173413","doi":"https://doi.org/10.1016/j.neucom.2026.133948"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133948","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133948","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2026.133948","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024390435","display_name":"David Orlando Salazar Torres","orcid":"https://orcid.org/0009-0000-3383-7681"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"David Orlando Salazar Torres","raw_affiliation_strings":["Department of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, L\u00fcbecker Ring 2, Soest, 59494, NRW, Germany"],"raw_orcid":"https://orcid.org/0009-0000-3383-7681","affiliations":[{"raw_affiliation_string":"Department of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, L\u00fcbecker Ring 2, Soest, 59494, NRW, Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093272758","display_name":"Diyar Altinses","orcid":"https://orcid.org/0009-0005-7928-5874"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Diyar Altinses","raw_affiliation_strings":["Department of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, L\u00fcbecker Ring 2, Soest, 59494, NRW, Germany"],"raw_orcid":"https://orcid.org/0009-0005-7928-5874","affiliations":[{"raw_affiliation_string":"Department of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, L\u00fcbecker Ring 2, Soest, 59494, NRW, Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025397538","display_name":"Andreas Schwung","orcid":"https://orcid.org/0000-0001-8405-0977"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Schwung","raw_affiliation_strings":["Department of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, L\u00fcbecker Ring 2, Soest, 59494, NRW, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8405-0977","affiliations":[{"raw_affiliation_string":"Department of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, L\u00fcbecker Ring 2, Soest, 59494, NRW, Germany","institution_ids":["https://openalex.org/I3130920692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024390435"],"corresponding_institution_ids":["https://openalex.org/I3130920692"],"apc_list":{"value":2670,"currency":"USD","value_usd":2670},"apc_paid":{"value":2670,"currency":"USD","value_usd":2670},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48194675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"694","issue":null,"first_page":"133948","last_page":"133948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.16519999504089355,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.16519999504089355,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.14640000462532043,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.10660000145435333,"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/initialization","display_name":"Initialization","score":0.8873000144958496},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5910000205039978},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5810999870300293},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46889999508857727},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.44200000166893005},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.44119998812675476},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43630000948905945},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8873000144958496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652999758720398},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4763999879360199},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.44119998812675476},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26829999685287476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133948","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133948","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"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2026.133948","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133948","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/F738684315","display_name":"Fachhochschule S\u00fcdwestfalen","ror":"https://ror.org/04t5phd24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3173369353","https://openalex.org/W3206782003","https://openalex.org/W4309890841","https://openalex.org/W4323276332","https://openalex.org/W4388153422","https://openalex.org/W4389879609","https://openalex.org/W4391853495","https://openalex.org/W4393144919","https://openalex.org/W4396623069","https://openalex.org/W4399220598","https://openalex.org/W4404328505","https://openalex.org/W4407937082","https://openalex.org/W4408867573","https://openalex.org/W4410951697","https://openalex.org/W4412088155","https://openalex.org/W4412931414","https://openalex.org/W4414778772","https://openalex.org/W4417147748","https://openalex.org/W7139070771"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"network":[1,80,200],"architectures":[2,210],"designed":[3],"for":[4,85],"function":[5],"parameterization,":[6],"such":[7],"as":[8,38],"the":[9,14,17,23,45,49,68,75,86,95,149,154,167,190],"Bag-of-Functions":[10],"(BoF)":[11],"framework,":[12],"bridge":[13],"gap":[15],"between":[16],"expressivity":[18],"of":[19,25,48,74,151],"deep":[20],"learning":[21],"and":[22,71,82,107,110,180,185,202,219,231],"interpretability":[24],"classical":[26],"signal":[27],"processing.":[28],"However,":[29],"these":[30],"models":[31],"are":[32],"inherently":[33],"sensitive":[34],"to":[35,43,54,77,99,115,173],"parameter":[36],"initialization,":[37],"traditional":[39],"data-agnostic":[40],"schemes":[41],"fail":[42],"capture":[44],"structural":[46,121],"properties":[47],"target":[50],"signals,":[51],"often":[52],"leading":[53],"suboptimal":[55],"convergence.":[56],"In":[57],"this":[58,120,152],"work,":[59],"we":[60],"propose":[61],"a":[62,111,124,174],"prior-informed":[63],"design":[64],"strategy":[65],"that":[66,93],"leverages":[67],"intrinsic":[69],"spectral":[70,196],"temporal":[72],"structure":[73],"data":[76],"guide":[78,198],"both":[79],"initialization":[81,156,201,207],"architectural":[83],"configuration":[84],"Bag-of-Functions.":[87],"A":[88,134],"principled":[89],"methodology":[90],"is":[91],"introduced":[92],"uses":[94],"Fast":[96],"Fourier":[97],"Transform":[98],"extract":[100],"dominant":[101],"seasonal":[102],"priors,":[103],"informing":[104],"model":[105,178],"depth":[106,203],"initial":[108],"states,":[109],"residual-based":[112],"regression":[113],"approach":[114],"parameterize":[116],"trend":[117,141],"components.":[118],"Crucially,":[119],"alignment":[122],"enables":[123,208],"substantial":[125],"reduction":[126,170],"in":[127,177],"encoder":[128],"dimensionality":[129,169],"without":[130,188,211],"compromising":[131],"reconstruction":[132,158],"fidelity.":[133],"supporting":[135],"theoretical":[136],"analysis":[137],"provides":[138],"guidance":[139],"on":[140,162],"estimation":[142],"under":[143],"finite-sample":[144],"regimes.":[145],"Extensive":[146],"experiments":[147],"demonstrate":[148],"effectiveness":[150],"approach:":[153],"informed":[155],"reduces":[157],"error":[159],"by":[160],"15.1%":[161],"complex":[163],"real-world":[164],"benchmarks.":[165],"Furthermore,":[166],"trend-informed":[168],"yields":[171],"up":[172],"30%":[175],"decrease":[176],"parameters":[179,230],"computational":[181,232],"complexity,":[182],"accelerating":[183],"inference":[184],"stabilizing":[186],"optimization":[187,218],"altering":[189],"core":[191],"training":[192],"procedure.":[193],"\u2022":[194,205,214,224],"Data-driven":[195],"priors":[197,216],"neural":[199],"selection.":[204],"Trend-informed":[206],"compact":[209],"accuracy":[212],"loss.":[213],"Informed":[215],"stabilize":[217],"accelerate":[220],"convergence":[221],"across":[222],"datasets.":[223],"Improved":[225],"efficiency":[226],"achieved":[227],"with":[228],"reduced":[229],"cost.":[233]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-05-15T00:00:00"}