{"id":"https://openalex.org/W3011770069","doi":"https://doi.org/10.1049/iet-ipr.2019.0761","title":"Accelerating convolutional neural network training using ProMoD backpropagation algorithm","display_name":"Accelerating convolutional neural network training using ProMoD backpropagation algorithm","publication_year":2020,"publication_date":"2020-03-10","ids":{"openalex":"https://openalex.org/W3011770069","doi":"https://doi.org/10.1049/iet-ipr.2019.0761","mag":"3011770069"},"language":"en","primary_location":{"id":"doi:10.1049/iet-ipr.2019.0761","doi":"https://doi.org/10.1049/iet-ipr.2019.0761","is_oa":false,"landing_page_url":"https://doi.org/10.1049/iet-ipr.2019.0761","pdf_url":null,"source":{"id":"https://openalex.org/S83215360","display_name":"IET Image Processing","issn_l":"1751-9659","issn":["1751-9659","1751-9667"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-c","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IET Image Processing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"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/A5028610937","display_name":"Ahmet G\u00fcrhanl\u0131","orcid":"https://orcid.org/0000-0002-2568-7991","observed_orcids":["https://orcid.org/0000-0002-2568-7991"]},"institutions":[{"id":"https://openalex.org/I179948855","display_name":"Istanbul Ayd\u0131n University","ror":"https://ror.org/00qsyw664","country_code":"TR","type":"education","lineage":["https://openalex.org/I179948855"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Ahmet G\u00fcrhanl\u0131","raw_affiliation_strings":["Department of Computer Engineering Istanbul Aydin University Be\u015fyol Mah. \u0130n\u00f6n\u00fc Cad. No: 38 Sefak\u00f6y\u2013K\u00fc\u00e7\u00fck\u00e7ekmece Istanbul Turkey"],"raw_orcid":"https://orcid.org/0000-0002-2568-7991","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering Istanbul Aydin University Be\u015fyol Mah. \u0130n\u00f6n\u00fc Cad. No: 38 Sefak\u00f6y\u2013K\u00fc\u00e7\u00fck\u00e7ekmece Istanbul Turkey","institution_ids":["https://openalex.org/I179948855"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028610937"],"corresponding_institution_ids":["https://openalex.org/I179948855"],"apc_list":{"value":2740,"currency":"USD","value_usd":2740},"apc_paid":null,"fwci":0.1689,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.50277412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"14","issue":"13","first_page":"2957","last_page":"2964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.7445999979972839,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.7445999979972839,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.22599999606609344,"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/T10320","display_name":"Neural Networks and Applications","score":0.014299999922513962,"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/backpropagation","display_name":"backpropagation","score":0.6990000009536743},{"id":"https://openalex.org/keywords/convolutional-neural-network-training","display_name":"convolutional neural network training","score":0.824999988079071},{"id":"https://openalex.org/keywords/image-recognition","display_name":"image recognition","score":0.6230000257492065},{"id":"https://openalex.org/keywords/training-acceleration","display_name":"training acceleration","score":0.7599999904632568},{"id":"https://openalex.org/keywords/power-consumption","display_name":"power consumption","score":0.7590000033378601},{"id":"https://openalex.org/keywords/mnist","display_name":"MNIST","score":0.9309999942779541},{"id":"https://openalex.org/keywords/fashion-mnist","display_name":"Fashion-MNIST","score":0.8740000128746033},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.9139999747276306}],"concepts":[{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.9158464670181274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893290519714355},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6938893795013428},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6251493692398071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5847778916358948},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5835707187652588},{"id":"https://openalex.org/C98359873","wikidata":"https://www.wikidata.org/wiki/Q1320470","display_name":"Rprop","level":5,"score":0.5542165040969849},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48600348830223083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40697455406188965},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.35221007466316223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3359607756137848},{"id":"https://openalex.org/C177973122","wikidata":"https://www.wikidata.org/wiki/Q7860946","display_name":"Types of artificial neural networks","level":4,"score":0.21496230363845825},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1049/iet-ipr.2019.0761","doi":"https://doi.org/10.1049/iet-ipr.2019.0761","is_oa":false,"landing_page_url":"https://doi.org/10.1049/iet-ipr.2019.0761","pdf_url":null,"source":{"id":"https://openalex.org/S83215360","display_name":"IET Image Processing","issn_l":"1751-9659","issn":["1751-9659","1751-9667"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-c","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IET Image Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1980287119","https://openalex.org/W2008183381","https://openalex.org/W2020917271","https://openalex.org/W2097428361","https://openalex.org/W2132093718","https://openalex.org/W2146502635","https://openalex.org/W2170723803","https://openalex.org/W2521757446","https://openalex.org/W2559655401","https://openalex.org/W2624102231","https://openalex.org/W2780640153","https://openalex.org/W2936995161","https://openalex.org/W2952750365","https://openalex.org/W2980394168"],"related_works":["https://openalex.org/W4206233527","https://openalex.org/W3010010930","https://openalex.org/W1863534956","https://openalex.org/W3037987804","https://openalex.org/W2904596315","https://openalex.org/W2800732852","https://openalex.org/W3140124472","https://openalex.org/W3083664160","https://openalex.org/W3112454338","https://openalex.org/W7104297855"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2,34],"(CNNs)":[3],"play":[4],"an":[5,105],"important":[6],"role":[7],"in":[8,57,70,131,137,182],"image":[9,15,31,150],"recognition":[10,16,151],"applications.":[11],"Fast":[12],"training":[13,85,101,183],"of":[14,41,78,96,158,184],"systems":[17],"is":[18,43,55,60,67,125,147],"a":[19,46,62],"crucial":[20],"point,":[21],"because":[22],"the":[23,76,84,100,109,117,120,132,135,138,171,194],"system":[24],"should":[25],"be":[26],"trained":[27,36],"for":[28,169],"each":[29],"new":[30],"class.":[32],"These":[33],"are":[35,167],"using":[37,134],"lengthy":[38],"calculations.":[39],"Focus":[40],"engineering":[42],"on":[44,149],"obtaining":[45],"fast,":[47],"but":[48],"stable":[49],"optimisation":[50],"method.":[51],"Momentum":[52],"technique":[53],"which":[54],"used":[56,111,168],"backpropagation":[58],"algorithms":[59],"like":[61],"proportional\u2013integral":[63],"(PI)":[64],"controller":[65],"that":[66,176],"widely":[68,110],"employed":[69],"automatic":[71],"control":[72],"systems.":[73],"It":[74],"takes":[75],"integral":[77],"past":[79],"errors":[80],"and":[81,103,153,160,164,186,196],"helps":[82],"reaching":[83],"targets.":[86],"Proportional":[87],"+":[88,90],"momentum":[89,195],"derivative":[91],"(ProMoD)":[92],"method":[93,115,146],"adds":[94],"gradient":[95,198],"update":[97,140],"matrices":[98],"to":[99,193],"process":[102],"builds":[104],"optimiser":[106],"such":[107],"as":[108],"PI\u2013derivative":[112],"controller.":[113],"The":[114],"accelerates":[116],"movement":[118],"toward":[119],"target":[121],"accuracy":[122],"levels.":[123],"This":[124],"achieved":[126],"by":[127],"doing":[128],"bigger":[129],"corrections":[130],"beginning":[133],"differences":[136],"calculated":[139],"matrices.":[141],"In":[142],"this":[143],"research,":[144],"ProMoD":[145,177],"tested":[148],"applications":[152],"CNNs.":[154],"Modified":[155],"national":[156],"institute":[157],"standards":[159],"technology":[161],"database":[162],"(MNIST)":[163],"Fashion\u2010MNIST":[165],"datasets":[166],"evaluating":[170],"performance.":[172],"Experimental":[173],"results":[174],"showed":[175],"might":[178],"perform":[179],"much":[180],"faster":[181],"CNNs":[185],"consume":[187],"proportionally":[188],"less":[189],"power":[190],"with":[191],"respect":[192],"stochastic":[197],"descent":[199],"(SGD)":[200],"techniques.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-03-23T00:00:00"}