{"id":"https://openalex.org/W2157812026","doi":"https://doi.org/10.1109/ijcnn.2011.6033191","title":"Efficient Levenberg-Marquardt minimization of the cross-entropy error function","display_name":"Efficient Levenberg-Marquardt minimization of the cross-entropy error function","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2157812026","doi":"https://doi.org/10.1109/ijcnn.2011.6033191","mag":"2157812026"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2011.6033191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2011.6033191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2011 International Joint Conference on Neural Networks","raw_type":"proceedings-article"},"type":"article","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/A5031170439","display_name":"Amar Saric","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amar Saric","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101669698","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0002-5675-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8793,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8153042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9972000122070312,"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":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8500908017158508},{"id":"https://openalex.org/keywords/levenberg\u2013marquardt-algorithm","display_name":"Levenberg\u2013Marquardt algorithm","score":0.7955945134162903},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.7037469148635864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6429975032806396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5155046582221985},{"id":"https://openalex.org/keywords/error-function","display_name":"Error function","score":0.4932054877281189},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48271867632865906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47606322169303894},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4647841453552246},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4547227919101715},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.45381778478622437},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44772204756736755},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.42543599009513855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3963882625102997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35447585582733154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2518596649169922}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8500908017158508},{"id":"https://openalex.org/C87578567","wikidata":"https://www.wikidata.org/wiki/Q1426494","display_name":"Levenberg\u2013Marquardt algorithm","level":3,"score":0.7955945134162903},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.7037469148635864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6429975032806396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5155046582221985},{"id":"https://openalex.org/C202286095","wikidata":"https://www.wikidata.org/wiki/Q579262","display_name":"Error function","level":2,"score":0.4932054877281189},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48271867632865906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47606322169303894},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4647841453552246},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4547227919101715},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.45381778478622437},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44772204756736755},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.42543599009513855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3963882625102997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35447585582733154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2518596649169922},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2011.6033191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2011.6033191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2011 International Joint Conference on Neural Networks","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1554663460","https://openalex.org/W1689766768","https://openalex.org/W1760551737","https://openalex.org/W2025357764","https://openalex.org/W2085924714","https://openalex.org/W2087070363","https://openalex.org/W2105471083","https://openalex.org/W2147632385","https://openalex.org/W2155482699","https://openalex.org/W2236623899","https://openalex.org/W2256578114","https://openalex.org/W2296319761","https://openalex.org/W3120740533","https://openalex.org/W4242676341","https://openalex.org/W4250589301","https://openalex.org/W4301491118"],"related_works":["https://openalex.org/W4292054264","https://openalex.org/W4287869072","https://openalex.org/W3170224572","https://openalex.org/W3005627584","https://openalex.org/W4285326772","https://openalex.org/W4367154275","https://openalex.org/W2913125146","https://openalex.org/W2952321997","https://openalex.org/W2792643794","https://openalex.org/W2911303748"],"abstract_inverted_index":{"The":[0],"Levenberg-Marquardt":[1,122],"algorithm":[2,123],"is":[3,71,77,97],"one":[4,152],"of":[5,30,60,81,89,108,120,176],"the":[6,28,50,56,61,65,74,78,82,90,93,121,127,137,146,173,177],"most":[7],"common":[8],"choices":[9],"for":[10,43,125,166],"training":[11,29,111,157],"medium-size":[12],"artificial":[13],"neural":[14,31,141],"networks.":[15,142],"Since":[16],"it":[17],"was":[18],"designed":[19],"to":[20,27,38,55,103,132,172],"solve":[21],"nonlinear":[22],"least-squares":[23],"problems,":[24],"its":[25],"applications":[26],"networks":[32],"have":[33],"so":[34],"far":[35],"typically":[36],"amounted":[37],"using":[39,145],"simple":[40],"regression":[41],"even":[42],"classification":[44,168],"tasks.":[45],"However,":[46],"in":[47,73,92,136,151,162],"this":[48],"case":[49],"cross-entropy":[51,128,147],"function,":[52,129],"which":[53,101],"corresponds":[54],"maximum":[57],"likelihood":[58],"estimate":[59],"network":[62],"weights":[63,91],"when":[64,170],"sigmoid":[66],"or":[67],"softmax":[68],"activation":[69],"function":[70,84,88],"used":[72],"output":[75,94],"layer,":[76],"natural":[79],"choice":[80],"error":[83,148,154],"and":[85,115],"a":[86,104,117,134],"convex":[87],"layer.":[95],"It":[96],"an":[98],"important":[99],"property":[100],"leads":[102],"more":[105],"robust":[106],"convergence":[107],"any":[109],"descent-based":[110],"method.":[112],"By":[113],"constructing":[114],"implementing":[116],"modified":[118],"version":[119],"suitable":[124],"minimizing":[126],"we":[130],"aim":[131],"close":[133],"gap":[135],"existing":[138],"literature":[139],"on":[140],"Additionally,":[143],"as":[144],"measure":[149],"results":[150,161],"single":[153],"value":[155],"per":[156],"pattern,":[158],"our":[159],"approach":[160],"lower":[163],"memory":[164],"requirements":[165],"multi-valued":[167],"problems":[169],"compared":[171],"direct":[174],"application":[175],"algorithm.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}