{"id":"https://openalex.org/W2467163293","doi":null,"title":"Stochastic Gradient Descent Algorithm in the Computational Network Toolkit","display_name":"Stochastic Gradient Descent Algorithm in the Computational Network Toolkit","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2467163293","mag":"2467163293"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.487.8737","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.487.8737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/people/bguenter/docs/cntk_nips2013 (2).pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W2467163293"],"child_works_count":0,"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/A5060197083","display_name":"Brian K. Guenter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Guenter","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844","observed_orcids":["https://orcid.org/0000-0003-0520-6844"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":"https://orcid.org/0000-0003-0520-6844","affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032414450","display_name":"Adam Eversole","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Eversole","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048403564","display_name":"Oleksii Kuchaiev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleksii Kuchaiev","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113773386","display_name":"Mike Seltzer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Seltzer","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.3024,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8006513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9765999913215637,"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":0.9765999913215637,"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/T10320","display_name":"Neural Networks and Applications","score":0.015699999406933784,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00279999990016222,"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/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.996999979019165},{"id":"https://openalex.org/keywords/automatic-differentiation","display_name":"automatic differentiation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/gradient-computation","display_name":"gradient computation","score":0.8230000138282776},{"id":"https://openalex.org/keywords/learning-rate-selection","display_name":"learning rate selection","score":0.8799999952316284},{"id":"https://openalex.org/keywords/log-linear-models","display_name":"log-linear models","score":0.6859999895095825},{"id":"https://openalex.org/keywords/directed-acyclic-graphs","display_name":"directed acyclic graphs","score":0.6790000200271606},{"id":"https://openalex.org/keywords/machine-learning-toolkit","display_name":"machine learning toolkit","score":0.5789999961853027},{"id":"https://openalex.org/keywords/c","display_name":"C++","score":0.5149999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71375572681427},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5323828458786011},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5321701169013977},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5103849768638611},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.475887656211853},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.473458468914032},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46889156103134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45365869998931885},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43811625242233276},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4356241226196289},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.42202141880989075},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.2236824333667755},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.487.8737","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.487.8737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/people/bguenter/docs/cntk_nips2013 (2).pdf","raw_type":"text"},{"id":"mag:2467163293","doi":null,"is_oa":false,"landing_page_url":"https://research.microsoft.com/en-us/um/people/bguenter/docs/cntk_nips2013%20(2).pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":"https://openalex.org/P4404678063","host_organization_name":"Neural Information Processing Systems Foundation","host_organization_lineage":["https://openalex.org/P4404678063"],"host_organization_lineage_names":["Neural Information Processing Systems Foundation"],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","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":5,"referenced_works":["https://openalex.org/W1904365287","https://openalex.org/W2008057734","https://openalex.org/W2120420045","https://openalex.org/W2146917784","https://openalex.org/W2153375074"],"related_works":["https://openalex.org/W2181607856","https://openalex.org/W1903676646","https://openalex.org/W2513383847","https://openalex.org/W7108228100","https://openalex.org/W4413857289","https://openalex.org/W4365518829","https://openalex.org/W2897963792","https://openalex.org/W2753012705","https://openalex.org/W2914390046","https://openalex.org/W2480518356"],"abstract_inverted_index":{"We":[0,37,51],"introduce":[1],"the":[2,9,39,44,127,133],"stochastic":[3],"gradient":[4],"descent":[5],"algorithm":[6,40,60],"used":[7,41,153],"in":[8,22,67,81,132,177],"computational":[10,35,74],"network":[11,75,176],"toolkit":[12,20],"(CNTK)":[13],"\u2014":[14],"a":[15,34,48,54,78,90,106,115,164],"general":[16],"purpose":[17],"machine":[18],"learning":[19,57],"written":[21],"C++":[23],"for":[24,47],"training":[25,166],"and":[26,61,93,121,168],"using":[27],"models":[28],"that":[29,63],"can":[30,146],"be":[31],"expressed":[32],"as":[33,126],"network.":[36,50],"describe":[38],"to":[42],"compute":[43],"gradients":[45],"automatically":[46],"given":[49],"also":[52],"propose":[53],"low-cost":[55],"automatic":[56],"rate":[58],"selection":[59],"demonstrate":[62],"it":[64],"works":[65],"well":[66],"practice.":[68],"1":[69,100,179],"Computational":[70],"Network":[71],"Toolkit":[72],"A":[73,144],"(CN)":[76],"is":[77,112,139],"directed":[79],"graph":[80],"which":[82,138,151],"each":[83,94,110],"leaf":[84],"represents":[85,96],"an":[86,97,102,172],"input":[87],"value":[88],"or":[89],"learnable":[91],"parameter":[92],"node":[95,111,161,184],"operator.":[98],"Figure":[99,178],"illustrates":[101],"example":[103],"CN":[104,145],"of":[105],"log-linear":[107],"model.":[108],"Here,":[109],"identified":[113],"by":[114],"{node":[116],"name:":[117],"operator":[118],"type}":[119],"pair":[120],"takes":[122],"its":[123],"ordered":[124],"children":[125],"operator\u2019s":[128],"inputs.":[129],"For":[130,157],"example,":[131,158],"figure,":[134],"T":[135],"=":[136,142],"Times(W,X)":[137],"different":[140,155],"fromT":[141],"Times(X,W).":[143],"have":[147],"many":[148],"root":[149,160,183],"nodes":[150],"are":[152],"under":[154],"conditions.":[156],"one":[159,182],"may":[162,170],"represent":[163,171],"cross-entropy":[165],"criterion":[167],"another":[169],"evaluation":[173],"criterion.":[174],"The":[175],"has":[180],"only":[181],"{C:":[185],"Cross":[186]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-07-22T00:00:00"}