{"id":"https://openalex.org/W1980287119","doi":"https://doi.org/10.1016/s0893-6080(98)00116-6","title":"On the momentum term in gradient descent learning algorithms","display_name":"On the momentum term in gradient descent learning algorithms","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W1980287119","doi":"https://doi.org/10.1016/s0893-6080(98)00116-6","mag":"1980287119","pmid":"https://pubmed.ncbi.nlm.nih.gov/12662723"},"language":"en","primary_location":{"id":"doi:10.1016/s0893-6080(98)00116-6","is_oa":true,"landing_page_url":"https://doi.org/10.1016/s0893-6080(98)00116-6","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/s0893-6080(98)00116-6","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101926903","display_name":"Ning Qian","orcid":"https://orcid.org/0000-0001-5168-9379"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ning Qian","raw_affiliation_strings":["Center for Neurobiology and Behavior, Columbia University, 722 W. 168th Street, New York, USA","Center for Neurobiology and Behavior, Columbia University, 722 W 168th Street, New York, NY 10032, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Neurobiology and Behavior, Columbia University, 722 W. 168th Street, New York, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Center for Neurobiology and Behavior, Columbia University, 722 W 168th Street, New York, NY 10032, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101926903"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":2.603,"has_fulltext":false,"cited_by_count":2339,"citation_normalized_percentile":{"value":0.90143958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"145","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9937000274658203,"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/momentum","display_name":"Momentum (technical analysis)","score":0.7829084396362305},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6563259959220886},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5892049074172974},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5708694458007812},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.560224711894989},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5064123868942261},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4343586564064026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4216199815273285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4073147773742676},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.376559317111969},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3461444675922394},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2825345993041992},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.21901416778564453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.200557678937912},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.10210651159286499}],"concepts":[{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.7829084396362305},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6563259959220886},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5892049074172974},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5708694458007812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.560224711894989},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5064123868942261},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4343586564064026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4216199815273285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4073147773742676},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.376559317111969},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3461444675922394},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2825345993041992},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.21901416778564453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.200557678937912},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.10210651159286499},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/s0893-6080(98)00116-6","is_oa":true,"landing_page_url":"https://doi.org/10.1016/s0893-6080(98)00116-6","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:12662723","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12662723","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":"Neural networks : the official journal of the International Neural Network Society","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.57.5612","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.5612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://brahms.cpmc.columbia.edu/publications/momentum.ps.Z","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1016/s0893-6080(98)00116-6","is_oa":true,"landing_page_url":"https://doi.org/10.1016/s0893-6080(98)00116-6","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1534755124","https://openalex.org/W1589549454","https://openalex.org/W1646429301","https://openalex.org/W2114766824","https://openalex.org/W2119423166","https://openalex.org/W2154642048","https://openalex.org/W2160208155","https://openalex.org/W2170120409","https://openalex.org/W2332984095","https://openalex.org/W2766736793","https://openalex.org/W3207342693","https://openalex.org/W4240701545","https://openalex.org/W4300402905","https://openalex.org/W6636956376","https://openalex.org/W6677103964"],"related_works":["https://openalex.org/W2353396818","https://openalex.org/W2370473919","https://openalex.org/W2762984199","https://openalex.org/W2390496461","https://openalex.org/W2389654532","https://openalex.org/W1517908938","https://openalex.org/W2369545560","https://openalex.org/W2355429547","https://openalex.org/W3090423162","https://openalex.org/W2162941631"],"abstract_inverted_index":{"A":[0],"momentum":[1,50,92,136,142],"term":[2,21,93,143],"is":[3,15,52,80,161],"usually":[4],"included":[5],"in":[6,43,66,122],"the":[7,24,44,49,55,74,95,105,117,129,141,146,153],"simulations":[8],"of":[9,26,34,46,57,73,85,97,104,148],"connectionist":[10],"learning":[11,149],"algorithms.":[12],"Although":[13],"it":[14],"well":[16],"known":[17],"that":[18,42,60,140],"such":[19],"a":[20,63,67,77,83],"greatly":[22],"improves":[23,94],"speed":[25,96],"learning,":[27],"there":[28],"have":[29],"been":[30],"few":[31],"rigorous":[32],"studies":[33],"its":[35],"mechanisms.":[36],"In":[37,125],"this":[38],"paper,":[39],"I":[40,127],"show":[41],"limit":[45],"continuous":[47],"time,":[48],"parameter":[51],"analogous":[53],"to":[54,82,108],"mass":[56],"Newtonian":[58],"particles":[59],"move":[61],"through":[62],"viscous":[64],"medium":[65],"conservative":[68],"force":[69],"field.":[70],"The":[71,91,156],"behavior":[72],"system":[75,106,154],"near":[76],"local":[78],"minimum":[79],"equivalent":[81],"set":[84],"coupled":[86],"and":[87,135,138],"damped":[88],"harmonic":[89],"oscillators.":[90],"convergence":[98,132,160],"by":[99],"bringing":[100],"some":[101],"eigen":[102],"components":[103],"closer":[107],"critical":[109],"damping.":[110],"Similar":[111],"results":[112],"can":[113,144],"be":[114],"obtained":[115],"for":[116,131,159],"discrete":[118],"time":[119],"case":[120],"used":[121],"computer":[123],"simulations.":[124],"particular,":[126],"derive":[128],"bounds":[130],"on":[133],"learning-rate":[134],"parameters,":[137],"demonstrate":[139],"increase":[145],"range":[147],"rate":[150],"over":[151],"which":[152],"converges.":[155],"optimal":[157],"condition":[158],"also":[162],"analyzed.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":158},{"year":2024,"cited_by_count":202},{"year":2023,"cited_by_count":250},{"year":2022,"cited_by_count":273},{"year":2021,"cited_by_count":382},{"year":2020,"cited_by_count":354},{"year":2019,"cited_by_count":297},{"year":2018,"cited_by_count":145},{"year":2017,"cited_by_count":97},{"year":2016,"cited_by_count":28},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}