{"id":"https://openalex.org/W1526055535","doi":null,"title":"Experiments on Learning by Back Propagation.","display_name":"Experiments on Learning by Back Propagation.","publication_year":1986,"publication_date":"1986-06-01","ids":{"openalex":"https://openalex.org/W1526055535","mag":"1526055535"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.878","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cnbc.cmu.edu/~plaut/papers/pdf/PlautNowlanHinton86TR.backprop.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5015410454","display_name":"David C. Plaut","orcid":"https://orcid.org/0000-0002-0399-7120","observed_orcids":["https://orcid.org/0000-0002-0399-7120"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David C. Plaut","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0399-7120","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047023054","display_name":"Steven J. Nowlan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven J. Nowlan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geoffrey E. Hinton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5582,"has_fulltext":false,"cited_by_count":323,"citation_normalized_percentile":{"value":0.96162658,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":9.999999747378752e-05,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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":0.9039999842643738},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.7319999933242798},{"id":"https://openalex.org/keywords/error-surface","display_name":"error surface","score":0.5730000138282776},{"id":"https://openalex.org/keywords/weight-space","display_name":"weight space","score":0.7129999995231628},{"id":"https://openalex.org/keywords/learning-speed","display_name":"learning speed","score":0.8740000128746033},{"id":"https://openalex.org/keywords/acceleration-techniques","display_name":"acceleration techniques","score":0.5580000281333923},{"id":"https://openalex.org/keywords/fan-in","display_name":"fan-in","score":0.6489999890327454},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.6660000085830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6079164147377014},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.526970624923706},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5217245817184448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49641066789627075},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49272778630256653},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4848121702671051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4615604281425476},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.45133334398269653},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44553661346435547},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.423493891954422},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08375895023345947},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.878","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cnbc.cmu.edu/~plaut/papers/pdf/PlautNowlanHinton86TR.backprop.pdf","raw_type":"text"},{"id":"mag:1526055535","doi":null,"is_oa":false,"landing_page_url":"https://apps.dtic.mil/dtic/tr/fulltext/u2/a180358.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W413857758","https://openalex.org/W1597286183","https://openalex.org/W1980658026","https://openalex.org/W2024060531","https://openalex.org/W2042492924","https://openalex.org/W2128084896","https://openalex.org/W2155487652","https://openalex.org/W2157629899","https://openalex.org/W2766736793"],"related_works":["https://openalex.org/W7096838861","https://openalex.org/W2021774695","https://openalex.org/W1498436455","https://openalex.org/W7096575033","https://openalex.org/W2096087480","https://openalex.org/W7098157345","https://openalex.org/W7099096599","https://openalex.org/W2895967366","https://openalex.org/W1541007220","https://openalex.org/W3147765605"],"abstract_inverted_index":{"Rumelhart,":[0],"Hinton":[1],"and":[2,42,110,140,151,201,216,224,227],"Williams":[3],"[Rumelhart":[4],"et":[5],"al.":[6],"86]":[7],"describe":[8],"a":[9,55,58,107,257],"learning":[10,26,40,77,127,174,188,231],"procedure":[11,128,189,232],"for":[12,106,249],"layered":[13],"networks":[14,215,220],"of":[15,60,72,76,84,99,102,125,137,156,165,176,179,186,240,253],"deterministic,":[16],"neuron-like":[17],"units.":[18,167],"This":[19],"paper":[20],"describes":[21],"further":[22],"research":[23],"on":[24,81,149,162,173],"the":[25,32,34,39,43,70,82,85,89,100,103,126,130,135,138,141,154,157,163,166,171,177,182,187,204,210,217,251,254],"procedure.":[27,206],"We":[28,48,96,144],"start":[29],"by":[30,88,222],"describing":[31],"units,":[33],"way":[35,131],"they":[36],"are":[37],"connected,":[38],"procedure,":[41],"extension":[44],"to":[45,65],"iterative":[46,214],"nets.":[47],"then":[49],"give":[50,97,145],"an":[51,113,246],"example":[52],"in":[53,69,92,119,237],"which":[54],"network":[56,142],"learns":[57],"set":[59],"filters":[61],"that":[62,190],"enable":[63],"it":[64,132],"discriminate":[66],"formant-like":[67],"patterns":[68],"presence":[71],"noise.":[73],"The":[74,122,230],"speed":[75,175],"is":[78,129,199],"strongly":[79],"dependent":[80],"shape":[83,101],"surface":[86,105],"formed":[87],"error":[90,104,197],"measure":[91],"\"weight":[93],"space.":[94,121],"\"":[95,219],"examples":[98],"typical":[108],"task":[109,139],"illustrate":[111,170],"how":[112,153],"acceleration":[114],"method":[115],"speeds":[116],"up":[117],"descent":[118],"weight":[120,159],"main":[123],"drawback":[124],"scales":[133],"as":[134,242,244],"size":[136],"increases.":[143],"some":[146],"preliminary":[147],"results":[148,169],"scaling":[150],"show":[152],"magnitude":[155],"optimal":[158,247],"changes":[160],"depends":[161],"fan-in":[164],"Additional":[168],"effects":[172],"amount":[178],"interaction":[180],"between":[181,212],"weights.":[183],"A":[184],"variation":[185],"back-propagates":[191],"desired":[192],"state":[193],"information":[194],"rather":[195],"than":[196],"gradients":[198],"developed":[200],"compared":[202],"with":[203],"standard":[205],"Finally,":[207],"we":[208],"discuss":[209],"relationship":[211],"our":[213],"\"analog":[218],"described":[221],"Hopfield":[223],"Tank":[225,228],"[Hopfield":[226],"85].":[229],"can":[233],"discover":[234],"appropriate":[235],"weights":[236],"their":[238],"kind":[239],"network,":[241],"well":[243],"determine":[245],"schedule":[248],"varying":[250],"nonlinearity":[252],"units":[255],"during":[256],"search.":[258],"1.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}