{"id":"https://openalex.org/W2734574836","doi":"https://doi.org/10.1109/ijcnn.2017.7966360","title":"Training neural networks with policy gradient","display_name":"Training neural networks with policy gradient","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2734574836","doi":"https://doi.org/10.1109/ijcnn.2017.7966360","mag":"2734574836"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7966360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","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/A5030977697","display_name":"Sourabh Bose","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sourabh Bose","raw_affiliation_strings":["Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manfred Huber","raw_affiliation_strings":["Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030977697"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08098849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"14","issue":null,"first_page":"3998","last_page":"4005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9986000061035156,"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/T12676","display_name":"Machine Learning and ELM","score":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9908000230789185,"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":0.9904000163078308,"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/autoencoder","display_name":"Autoencoder","score":0.7462146282196045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7070115208625793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6859139204025269},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6021614074707031},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5352708697319031},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.528588056564331},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5082795023918152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49371132254600525},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.4749372601509094},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40594977140426636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19263604283332825}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7462146282196045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070115208625793},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6859139204025269},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6021614074707031},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5352708697319031},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.528588056564331},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5082795023918152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49371132254600525},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.4749372601509094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40594977140426636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19263604283332825},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7966360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1825869920","https://openalex.org/W2004586880","https://openalex.org/W2031823405","https://openalex.org/W2058670155","https://openalex.org/W2118309135","https://openalex.org/W2119850747","https://openalex.org/W2124175081","https://openalex.org/W2130801532","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2161977692","https://openalex.org/W2164641162","https://openalex.org/W2342662072","https://openalex.org/W2963864421","https://openalex.org/W4211092921","https://openalex.org/W4214717370","https://openalex.org/W4302570325","https://openalex.org/W6678113768","https://openalex.org/W6678114464","https://openalex.org/W6679257226","https://openalex.org/W6683204974","https://openalex.org/W6684054434","https://openalex.org/W6704571135"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"are":[2,42,81,85],"a":[3,23,59,110,145,217,222,250],"powerful":[4],"function":[5,15,21,32],"approximation":[6],"tool":[7],"which":[8,114,159],"has":[9],"the":[10,31,34,37,45,65,68,95,99,157,162,177,185,207,213,231,241],"ability":[11],"to":[12,29,63,118,127,156,175,183,248],"model":[13,189,243],"any":[14,20,202],"with":[16,88,227],"arbitrary":[17,203],"precision.":[18],"For":[19],"as":[22],"black":[24],"box,":[25],"it":[26,55,103,123,172,256],"is":[27,47,56,72,104,115,124,154,173,235,238,244],"able":[28,247],"reconstruct":[30],"given":[33],"target":[35,46],"and":[36,107,253],"input":[38],"data.":[39],"However,":[40,102],"there":[41],"problems":[43,143,192],"where":[44,78],"at":[48],"least":[49],"partially":[50],"unknown.":[51],"In":[52,148,169],"such":[53,132,149,191],"cases":[54,150],"impossible":[57],"for":[58,179,200],"traditional":[60,264],"neural":[61,208],"network":[62,209],"compute":[64],"gradient":[66,178,195,215],"of":[67,98,140,219,225,266],"system.":[69],"This":[70,197],"problem":[71],"evident":[73],"in":[74,94,109,138],"sparse":[75],"autoencoder":[76],"systems":[77],"lateral":[79,90,228],"inhibitions":[80,84,229],"required.":[82],"Lateral":[83],"usually":[86],"imposed":[87],"extra":[89],"connections":[91],"among":[92],"nodes":[93],"immediate":[96],"vicinity":[97],"hidden":[100,233],"layer.":[101],"computationally":[105],"expensive,":[106],"results":[108,262],"very":[111],"complex":[112],"architecture":[113],"not":[116,245],"scalable":[117],"real":[119],"world":[120],"problems.":[121],"Thus":[122],"often":[125],"necessary":[126,174],"achieve":[128,249],"structural":[129],"constraints":[130,205],"without":[131,144],"complexity":[133],"limitations.":[134],"Similar":[135],"situation":[136],"arises":[137],"case":[139],"multi-label":[141],"classification":[142],"known":[146],"target.":[147],"only":[151,246],"an":[152],"evaluation":[153],"accessible":[155],"network,":[158],"states":[160],"whether":[161],"sample":[163],"was":[164],"correctly":[165],"classified":[166],"or":[167,260],"not.":[168],"this":[170,180],"problem,":[171],"derive":[176],"partial":[181],"information":[182],"solve":[184],"problem.":[186],"The":[187],"proposed":[188,242],"solves":[190],"using":[193],"policy":[194],"algorithms.":[196],"approach":[198],"allows":[199],"imposing":[201],"non-differentiable":[204],"on":[206],"system":[210,218],"by":[211],"deriving":[212],"required":[214],"from":[216],"rewards.":[220],"Furthermore":[221],"novel":[223],"form":[224],"sparsity":[226],"over":[230],"entire":[232],"layer":[234],"proposed.":[236],"It":[237],"shown":[239],"that":[240],"much":[251],"tighter":[252],"sparser":[254],"representation,":[255],"also":[257],"achieves":[258],"similar":[259],"better":[261],"than":[263],"forms":[265],"sparsity.":[267]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}