{"id":"https://openalex.org/W4387006199","doi":"https://doi.org/10.1109/cec53210.2023.10253975","title":"Deep Learning Models Compression Based on Evolutionary Algorithms and Digital Fractional Differentiation","display_name":"Deep Learning Models Compression Based on Evolutionary Algorithms and Digital Fractional Differentiation","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4387006199","doi":"https://doi.org/10.1109/cec53210.2023.10253975"},"language":"en","primary_location":{"id":"doi:10.1109/cec53210.2023.10253975","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cec53210.2023.10253975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018242910","display_name":"Arcadi Llanza","orcid":"https://orcid.org/0000-0001-5928-3189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arcadi Llanza","raw_affiliation_strings":["Cyclope.ai University,Paris Est Créteil Laboratoire LISSI,Paris,France"],"raw_orcid":"https://orcid.org/0000-0001-5928-3189","affiliations":[{"raw_affiliation_string":"Cyclope.ai University,Paris Est Créteil Laboratoire LISSI,Paris,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007306111","display_name":"Fekhr Eddine Keddous","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fekhr Eddine Keddous","raw_affiliation_strings":["Cyclope.ai University,Paris Est Créteil Laboratoire LISSI,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cyclope.ai University,Paris Est Créteil Laboratoire LISSI,Paris,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050262088","display_name":"Nadiya Shvai","orcid":"https://orcid.org/0000-0001-8194-6196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nadiya Shvai","raw_affiliation_strings":["Cyclope.ai,Paris,France","Cyclope.ai, Paris, France"],"raw_orcid":"https://orcid.org/0000-0001-8194-6196","affiliations":[{"raw_affiliation_string":"Cyclope.ai,Paris,France","institution_ids":[]},{"raw_affiliation_string":"Cyclope.ai, Paris, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067068847","display_name":"Amir Nakib","orcid":"https://orcid.org/0000-0001-9620-9324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir Nakib","raw_affiliation_strings":["Cyclope.ai University,Paris Est Créteil Laboratoire LISSI,Paris,France"],"raw_orcid":"https://orcid.org/0000-0001-9620-9324","affiliations":[{"raw_affiliation_string":"Cyclope.ai University,Paris Est Créteil Laboratoire LISSI,Paris,France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13298154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","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/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9965999722480774,"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/mnist-database","display_name":"MNIST database","score":0.8382910490036011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6299358010292053},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6024135947227478},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5351698398590088},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4918324947357178},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.48756569623947144},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.47360873222351074},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.4485005736351013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44616666436195374},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.42871707677841187},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4143410325050354},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07958626747131348}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8382910490036011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6299358010292053},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6024135947227478},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5351698398590088},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4918324947357178},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.48756569623947144},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.47360873222351074},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.4485005736351013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44616666436195374},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.42871707677841187},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4143410325050354},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07958626747131348},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cec53210.2023.10253975","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cec53210.2023.10253975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04342525v1","is_oa":false,"landing_page_url":"https://hal.u-pec.fr/hal-04342525","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023 IEEE Congress on Evolutionary Computation (CEC), Jul 2023, Chicago, United States. pp.1-9, ⟨10.1109/CEC53210.2023.10253975⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1553338987","https://openalex.org/W1821462560","https://openalex.org/W1879678483","https://openalex.org/W1902934009","https://openalex.org/W1996901117","https://openalex.org/W2006136692","https://openalex.org/W2011394976","https://openalex.org/W2054529505","https://openalex.org/W2095835509","https://openalex.org/W2108704847","https://openalex.org/W2112036188","https://openalex.org/W2112796928","https://openalex.org/W2121775913","https://openalex.org/W2123066915","https://openalex.org/W2152195021","https://openalex.org/W2152710595","https://openalex.org/W2161411167","https://openalex.org/W2233116163","https://openalex.org/W2544912866","https://openalex.org/W2754084392","https://openalex.org/W2766839578","https://openalex.org/W2808868252","https://openalex.org/W2884022415","https://openalex.org/W2949964376","https://openalex.org/W2950248853","https://openalex.org/W3004543888","https://openalex.org/W3012561096","https://openalex.org/W3021613070","https://openalex.org/W3089812288","https://openalex.org/W3121369352","https://openalex.org/W3184606595","https://openalex.org/W3215972573","https://openalex.org/W4295312788","https://openalex.org/W4310147199","https://openalex.org/W4394650770","https://openalex.org/W6638523607","https://openalex.org/W6639703010","https://openalex.org/W6684563725","https://openalex.org/W6686067075","https://openalex.org/W6729471031","https://openalex.org/W6745499037","https://openalex.org/W6766978945","https://openalex.org/W6864327295"],"related_works":["https://openalex.org/W1512321724","https://openalex.org/W4231317009","https://openalex.org/W2367696392","https://openalex.org/W4383723869","https://openalex.org/W4293703255","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W1723410974"],"abstract_inverted_index":{"Neural":[0],"Networks":[1],"(NNs)":[2],"have":[3],"shown":[4],"excellent":[5],"results":[6,108],"in":[7,20,119,127,130,134],"a":[8,21],"variety":[9],"of":[10,24,29,36,44,75,121,142,154],"Machine":[11],"Learning":[12],"(ML)":[13],"tasks":[14],"and":[15,50,82,103,132],"are":[16,146],"now":[17],"being":[18],"used":[19],"wide":[22],"range":[23],"applications.":[25,67],"Meanwhile,":[26],"the":[27,37,73,76,104,137,143,155],"size":[28],"these":[30],"models":[31,41],"has":[32,54,60],"increased,":[33],"with":[34,123],"some":[35],"most":[38],"recent":[39],"state-of-the-art":[40],"comprising":[42],"billions":[43],"parameters.":[45],"The":[46,107],"necessity":[47],"for":[48,65],"compact":[49],"efficient":[51],"NN":[52],"representations":[53],"been":[55],"recognized":[56],"by":[57],"research,":[58],"which":[59],"provided":[61],"specialized":[62],"compression":[63,77,125],"techniques":[64],"various":[66],"In":[68],"this":[69,86],"paper,":[70],"we":[71],"propose":[72],"optimization":[74],"based":[78],"on":[79,110],"evolutionary":[80],"algorithms":[81],"fractional":[83,99],"differentiation.":[84],"To":[85],"end,":[87],"three":[88],"main":[89],"criteria":[90],"were":[91],"taken":[92],"into":[93],"account:":[94],"filters":[95],"error":[96],"approximation":[97],"using":[98],"differentiation,":[100],"NNs":[101],"accuracy":[102,122],"Compression":[105],"ratio.":[106],"obtained":[109],"LeNet5":[111],"model":[112],"demonstrated":[113],"that":[114,140],"there":[115],"is":[116],"no":[117],"loss":[118],"terms":[120],"50%":[124],"ratio":[126],"MNIST,":[128],"18%":[129],"CIFAR10,":[131],"9%":[133],"CIFAR100.":[135],"Moreover,":[136],"analysis":[138],"showed":[139],"kernels":[141],"first":[144],"layer":[145],"more":[147],"complex":[148],"to":[149],"be":[150],"compressed":[151],"than":[152],"those":[153],"second":[156],"layer.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}