{"id":"https://openalex.org/W3092484340","doi":"https://doi.org/10.1109/tnnls.2020.3027750","title":"Two-Phase Switching Optimization Strategy in Deep Neural Networks","display_name":"Two-Phase Switching Optimization Strategy in Deep Neural Networks","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3092484340","doi":"https://doi.org/10.1109/tnnls.2020.3027750","mag":"3092484340","pmid":"https://pubmed.ncbi.nlm.nih.gov/33048768"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3027750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3027750","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5082640331","display_name":"Hong Hui Tan","orcid":"https://orcid.org/0000-0003-0633-1292"},"institutions":[{"id":"https://openalex.org/I158949172","display_name":"Curtin University Sarawak","ror":"https://ror.org/024fm2y42","country_code":"MY","type":"education","lineage":["https://openalex.org/I158949172"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Hong Hui Tan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Curtin University Malaysia, Miri, Malaysia"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Curtin University Malaysia, Miri, Malaysia","institution_ids":["https://openalex.org/I158949172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060477744","display_name":"King Hann Lim","orcid":"https://orcid.org/0000-0002-5679-7747"},"institutions":[{"id":"https://openalex.org/I158949172","display_name":"Curtin University Sarawak","ror":"https://ror.org/024fm2y42","country_code":"MY","type":"education","lineage":["https://openalex.org/I158949172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"King Hann Lim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Curtin University Malaysia, Miri, Malaysia"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Curtin University Malaysia, Miri, Malaysia","institution_ids":["https://openalex.org/I158949172"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082640331"],"corresponding_institution_ids":["https://openalex.org/I158949172"],"apc_list":null,"apc_paid":null,"fwci":0.785,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.74857475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"1","first_page":"330","last_page":"339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9990000128746033,"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/T12676","display_name":"Machine Learning and ELM","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"}}],"keywords":[{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.8126617670059204},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.730616569519043},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.6929395198822021},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6296149492263794},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6206845045089722},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5926189422607422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5781251192092896},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5518553256988525},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5490697622299194},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5118369460105896},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4899868071079254},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.44163161516189575},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.43199506402015686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37504884600639343},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35299402475357056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2531849145889282},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.20829641819000244}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.8126617670059204},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.730616569519043},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.6929395198822021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6296149492263794},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6206845045089722},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5926189422607422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5781251192092896},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5518553256988525},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5490697622299194},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5118369460105896},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4899868071079254},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.44163161516189575},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.43199506402015686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37504884600639343},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35299402475357056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2531849145889282},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.20829641819000244},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.3027750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3027750","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:33048768","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33048768","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4477058665","display_name":null,"funder_award_id":"FRGS/1/2015/TK04/CURTIN/02/1","funder_id":"https://openalex.org/F4320321709","funder_display_name":"Ministry of Higher Education, Malaysia"}],"funders":[{"id":"https://openalex.org/F4320321709","display_name":"Ministry of Higher Education, Malaysia","ror":"https://ror.org/05mcs2t73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W59778349","https://openalex.org/W114517082","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1544152422","https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W1888884532","https://openalex.org/W1999380910","https://openalex.org/W2022508996","https://openalex.org/W2046609661","https://openalex.org/W2097117768","https://openalex.org/W2108604074","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2114053544","https://openalex.org/W2123585936","https://openalex.org/W2135520967","https://openalex.org/W2146502635","https://openalex.org/W2155482699","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2618530766","https://openalex.org/W2776855315","https://openalex.org/W2793290155","https://openalex.org/W2810018678","https://openalex.org/W2919115771","https://openalex.org/W2941034199","https://openalex.org/W2949935872","https://openalex.org/W3102143361","https://openalex.org/W3118608800","https://openalex.org/W4238404964","https://openalex.org/W4301014524","https://openalex.org/W6600284362","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6680285999","https://openalex.org/W6681435938","https://openalex.org/W6743446608","https://openalex.org/W6757751764","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2924468784","https://openalex.org/W4288259399","https://openalex.org/W2969529314","https://openalex.org/W2355987247","https://openalex.org/W4312206232","https://openalex.org/W3143650729","https://openalex.org/W3177326532","https://openalex.org/W4297883503","https://openalex.org/W2975301014","https://openalex.org/W2042173174"],"abstract_inverted_index":{"Optimization":[0],"in":[1,37,157],"a":[2,47],"deep":[3],"neural":[4],"network":[5,19],"is":[6,35,117,154],"always":[7],"challenging":[8],"due":[9],"to":[10,40,109,119,123,151,160],"the":[11,27,56,63,69,81,86,99,120,148,162],"vanishing":[12,163],"gradient":[13,164],"problem":[14],"and":[15,67,136],"intensive":[16],"fine-tuning":[17],"of":[18,88,101,147],"hyperparameters.":[20],"Inspired":[21],"by":[22],"multistage":[23],"decision":[24],"control":[25],"systems,":[26],"stochastic":[28],"diagonal":[29,70],"approximate":[30,111],"greatest":[31,82],"descent":[32],"(SDAGD)":[33],"algorithm":[34],"proposed":[36,53,149],"this":[38,158],"article":[39,159],"seek":[41],"for":[42,73],"optimal":[43,65,103,121],"learning":[44,134],"weights":[45],"using":[46],"two-phase":[48],"switching":[49],"optimization":[50,144],"strategy.":[51],"The":[52,127],"optimizer":[54,150],"controls":[55],"relative":[57],"step":[58,83],"length":[59,84],"derived":[60],"based":[61],"on":[62],"long-term":[64],"trajectory":[66],"adopts":[68],"approximated":[71],"Hessian":[72],"efficient":[74],"weight":[75],"update.":[76],"In":[77,105],"Phase-I,":[78],"it":[79,107,116],"computes":[80],"at":[85],"boundary":[87],"each":[89],"local":[90],"spherical":[91],"search":[92],"region":[93],"and,":[94],"subsequently,":[95],"descends":[96],"rapidly":[97],"toward":[98],"direction":[100],"an":[102,110],"solution.":[104],"Phase-II,":[106],"switches":[108],"Newton":[112],"method":[113],"automatically":[114],"once":[115],"closer":[118],"solution":[122],"achieve":[124],"fast":[125],"convergence.":[126],"experiments":[128],"show":[129],"that":[130],"SDAGD":[131],"produces":[132],"steeper":[133],"curves":[135],"achieves":[137],"lower":[138],"misclassification":[139],"rates":[140],"compared":[141],"with":[142],"other":[143],"techniques.":[145],"Implementation":[146],"deeper":[152],"networks":[153],"also":[155],"investigated":[156],"study":[161],"problem.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}