{"id":"https://openalex.org/W2897250287","doi":"https://doi.org/10.1109/cig.2018.8490455","title":"Building Evaluation Functions for Chess and Shogi with Uniformity Regularization Networks","display_name":"Building Evaluation Functions for Chess and Shogi with Uniformity Regularization Networks","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2897250287","doi":"https://doi.org/10.1109/cig.2018.8490455","mag":"2897250287"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2018.8490455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","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/A5015877402","display_name":"Shanchuan Wan","orcid":"https://orcid.org/0000-0002-3771-1522"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shanchuan Wan","raw_affiliation_strings":["Graduate School of Interdisciplinary Information Studies, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Interdisciplinary Information Studies, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103172324","display_name":"Tomoyuki Kaneko","orcid":"https://orcid.org/0000-0001-8051-2388"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyuki Kaneko","raw_affiliation_strings":["Interfaculty Initiative in Information Studies, The University of Tokyo, and JST, PRESTO"],"affiliations":[{"raw_affiliation_string":"Interfaculty Initiative in Information Studies, The University of Tokyo, and JST, PRESTO","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015877402"],"corresponding_institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.4006,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87392719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"529","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9965999722480774,"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/T12677","display_name":"Sports Dynamics and Biomechanics","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8550459146499634},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.851159930229187},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.831518828868866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7539706230163574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5567248463630676},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5347076654434204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5170838832855225},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.49732449650764465},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4706275463104248},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34523141384124756}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8550459146499634},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.851159930229187},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.831518828868866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539706230163574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5567248463630676},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5347076654434204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5170838832855225},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.49732449650764465},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4706275463104248},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34523141384124756},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2018.8490455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1497290640","https://openalex.org/W1583460156","https://openalex.org/W1750311484","https://openalex.org/W1896424170","https://openalex.org/W2095705004","https://openalex.org/W2099001564","https://openalex.org/W2144513243","https://openalex.org/W2151368309","https://openalex.org/W2156387975","https://openalex.org/W2165999534","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2509966261","https://openalex.org/W2590374252","https://openalex.org/W2593414223","https://openalex.org/W2626792426","https://openalex.org/W2766447205","https://openalex.org/W2772709170","https://openalex.org/W2800677456","https://openalex.org/W2911296969","https://openalex.org/W3098637454","https://openalex.org/W6629866293","https://openalex.org/W6634892453","https://openalex.org/W6637617981","https://openalex.org/W6639495226","https://openalex.org/W6674330103","https://openalex.org/W6681151457","https://openalex.org/W6682305990","https://openalex.org/W6682889407","https://openalex.org/W6734002484","https://openalex.org/W6739811675","https://openalex.org/W6746177919"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W3200695403","https://openalex.org/W4288087796","https://openalex.org/W2982339091","https://openalex.org/W4379087245","https://openalex.org/W2897250287"],"abstract_inverted_index":{"Building":[0],"evaluation":[1,44,167],"functions":[2,45,111],"for":[3,34,112,146,155,187,198],"chess":[4,199],"variants":[5],"is":[6,62,140,185],"a":[7,78,84,93,97,123,133,161],"challenging":[8],"goal.":[9],"At":[10],"this":[11],"time,":[12],"only":[13],"AlphaZero":[14],"succeeded":[15],"with":[16,68],"millions":[17],"of":[18,25,42,49,122,128,180,192],"self-play":[19],"records":[20],"produced":[21],"by":[22,82],"using":[23,54],"thousands":[24],"tensor":[26],"processing":[27],"units":[28],"(TPUs),":[29],"which":[30],"are":[31,71,107,114,173],"not":[32],"available":[33],"most":[35],"researchers.":[36],"This":[37],"paper":[38],"presents":[39],"the":[40,47,90,117,120,150,178,189,193,203,207],"challenge":[41],"training":[43,80,135],"on":[46,116],"basis":[48],"deep":[50],"convolutional":[51,102],"neural":[52],"networks":[53,106],"decent":[55],"data":[56,70],"and":[57,96,104,126,158,200,215],"computing":[58],"resources,":[59],"where":[60],"regularization":[61,86,184,213],"crucial":[63],"as":[64,132,160],"complex":[65],"models":[66],"trained":[67,108],"limited":[69],"more":[72],"prone":[73],"to":[74,142,169,177],"overfitting.":[75],"We":[76],"present":[77],"novel":[79],"scheme":[81],"introducing":[83],"uniformity":[85],"(UR)":[87],"network.":[88,195],"In":[89],"proposed":[91,204],"approach,":[92],"value":[94,138,194,221],"network":[95,99,139],"discriminator":[98,151],"share":[100],"common":[101],"layers":[103],"both":[105],"simultaneously.":[109],"Loss":[110],"them":[113],"based":[115],"difference":[118],"between":[119],"score":[121],"random":[124],"move":[125,131,156],"that":[127,163],"an":[129],"experts'":[130],"comparison":[134],"method.":[136],"The":[137],"expected":[141],"give":[143],"precise":[144],"scores":[145],"all":[147,171],"positions,":[148],"while":[149],"makes":[152],"qualitative":[153],"evaluations":[154],"pairs,":[157],"acts":[159],"regularizer":[162],"penalizes":[164],"differences":[165],"in":[166],"results":[168,197],"ensure":[170],"samples":[172],"uniformly":[174],"discriminated.":[175],"Due":[176],"existence":[179],"shared":[181],"layers,":[182],"such":[183],"beneficial":[186],"improving":[188],"overall":[190],"accuracy":[191],"Experimental":[196],"shogi":[201],"demonstrate":[202],"method":[205],"surpassed":[206],"standard":[208],"L":[209],"<sub":[210],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[211],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sub>":[212],"method,":[214],"successfully":[216],"helped":[217],"obtain":[218],"decently":[219],"accurate":[220],"networks.":[222]},"counts_by_year":[{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}