{"id":"https://openalex.org/W4394586017","doi":"https://doi.org/10.1109/access.2024.3385857","title":"A Generalist Reinforcement Learning Agent for Compressing Convolutional Neural Networks","display_name":"A Generalist Reinforcement Learning Agent for Compressing Convolutional Neural Networks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394586017","doi":"https://doi.org/10.1109/access.2024.3385857"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3385857","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3385857","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10494337.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10494337.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095044475","display_name":"Gabriel Gonzalez-Sahagun","orcid":"https://orcid.org/0009-0009-7931-4654"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Gabriel Gonzalez-Sahagun","raw_affiliation_strings":["School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028807044","display_name":"Santiago Enrique Conant-Pablos","orcid":"https://orcid.org/0000-0001-6270-3164"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Santiago Enrique Conant-Pablos","raw_affiliation_strings":["School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027131130","display_name":"Jos\u00e9 Carlos Ort\u00edz-Bayliss","orcid":"https://orcid.org/0000-0003-3408-2166"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Carlos Ortiz-Bayliss","raw_affiliation_strings":["School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086193689","display_name":"Jorge M. Cruz\u2010Duarte","orcid":"https://orcid.org/0000-0003-4494-7864"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jorge M. Cruz-Duarte","raw_affiliation_strings":["School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, Mexico","institution_ids":["https://openalex.org/I98461037"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5095044475"],"corresponding_institution_ids":["https://openalex.org/I98461037"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03565315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"51100","last_page":"51114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7799000144004822,"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":0.7799000144004822,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7907241582870483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891778349876404},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6954038739204407},{"id":"https://openalex.org/keywords/generalist-and-specialist-species","display_name":"Generalist and specialist species","score":0.5520291924476624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5452637076377869},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4143570065498352},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3818228840827942},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11466839909553528}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7907241582870483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891778349876404},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6954038739204407},{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.5520291924476624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5452637076377869},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4143570065498352},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3818228840827942},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11466839909553528},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C185933670","wikidata":"https://www.wikidata.org/wiki/Q52105","display_name":"Habitat","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3385857","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3385857","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10494337.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1429d0ceed844ca6820ced92ff25d756","is_oa":true,"landing_page_url":"https://doaj.org/article/1429d0ceed844ca6820ced92ff25d756","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 51100-51114 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3385857","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3385857","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10494337.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394586017.pdf","grobid_xml":"https://content.openalex.org/works/W4394586017.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1846799578","https://openalex.org/W1935978687","https://openalex.org/W2119144962","https://openalex.org/W2294370754","https://openalex.org/W2495425901","https://openalex.org/W2546536770","https://openalex.org/W2707890836","https://openalex.org/W2750384547","https://openalex.org/W2756085244","https://openalex.org/W2761873684","https://openalex.org/W2771111398","https://openalex.org/W2886851211","https://openalex.org/W2902907165","https://openalex.org/W2902986194","https://openalex.org/W2928560789","https://openalex.org/W2954507353","https://openalex.org/W2962965870","https://openalex.org/W2982316857","https://openalex.org/W3004543888","https://openalex.org/W3033108890","https://openalex.org/W3035414587","https://openalex.org/W3040786925","https://openalex.org/W3098951351","https://openalex.org/W3201902125","https://openalex.org/W4224950724","https://openalex.org/W4226284112","https://openalex.org/W4236853429","https://openalex.org/W4285179967","https://openalex.org/W4289705211","https://openalex.org/W4294560677","https://openalex.org/W4297775537","https://openalex.org/W4307927178","https://openalex.org/W4312900176","https://openalex.org/W4327572222","https://openalex.org/W4381281624","https://openalex.org/W4385566558","https://openalex.org/W4394670654","https://openalex.org/W6638026421","https://openalex.org/W6638444622","https://openalex.org/W6638677478","https://openalex.org/W6677067356","https://openalex.org/W6677580257","https://openalex.org/W6685444567","https://openalex.org/W6723181079","https://openalex.org/W6726275242","https://openalex.org/W6730382033","https://openalex.org/W6734621401","https://openalex.org/W6737664043","https://openalex.org/W6739917289","https://openalex.org/W6743688258","https://openalex.org/W6744495609","https://openalex.org/W6780449691","https://openalex.org/W6838557027","https://openalex.org/W6840499701"],"related_works":["https://openalex.org/W2306541987","https://openalex.org/W3135453479","https://openalex.org/W2947952289","https://openalex.org/W4322625948","https://openalex.org/W1986194836","https://openalex.org/W2896365120","https://openalex.org/W1986504168","https://openalex.org/W2095481932","https://openalex.org/W1454292034","https://openalex.org/W3173023979"],"abstract_inverted_index":{"Over":[0],"the":[1,10,20,98,101,111,157,162],"years,":[2],"researchers":[3],"have":[4,27],"proposed":[5],"multiple":[6],"approaches":[7],"to":[8,19,29,37,77,85,90,92,127,146,168],"reduce":[9],"number":[11],"of":[12,22,66,100,122,130,137,172,180],"parameters":[13],"Deep":[14,117],"Learning":[15,32],"models":[16],"have.":[17],"Due":[18],"complexity":[21],"compressing":[23,67],"models,":[24,150],"some":[25],"authors":[26],"opted":[28],"train":[30],"Reinforcement":[31],"agents":[33],"that":[34,72],"learn":[35],"how":[36],"compress":[38,147],"a":[39,58,62,115,120,131],"particular":[40],"model":[41,52],"without":[42],"losing":[43],"considerable":[44],"accuracy.":[45],"Nonetheless,":[46],"training":[47,61],"an":[48,177],"agent":[49,64,81,144],"for":[50,60,134],"each":[51],"can":[53],"be":[54],"time-consuming.":[55],"We":[56],"propose":[57],"methodology":[59],"generalist":[63,80,143],"capable":[65],"other":[68,158],"convolutional":[69,93],"neural":[70],"networks":[71],"it":[73,107,126],"was":[74],"not":[75],"trained":[76,145,152,165],"compress.":[78],"Our":[79,142],"uses":[82],"feature":[83,102,135],"maps":[84,103,136],"select":[86],"which":[87],"compression":[88],"technique":[89],"apply":[91],"and":[94,140,156],"dense":[95],"layers.":[96],"Since":[97],"shape":[99],"is":[104],"reduced":[105],"as":[106],"goes":[108],"deeper":[109],"into":[110],"network,":[112],"we":[113],"implemented":[114],"Dueling":[116],"Q-Network":[118],"with":[119,153,159,176],"Region":[121],"Interest":[123],"layer,":[124],"allowing":[125],"generate":[128],"features":[129],"fixed":[132],"size":[133,175],"various":[138],"heights":[139],"widths.":[141],"two":[148],"LeNet":[149],"one":[151],"fashion":[154],"MNIST":[155,167],"Kuzushiji-MNIST,":[160],"compressed":[161],"same":[163],"architecture":[164],"on":[166],"less":[169,181],"than":[170,182],"15%":[171],"its":[173],"original":[174],"accuracy":[178],"loss":[179],"2.5%.":[183]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}