Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2018087814) MULTI-TASK RELATIONSHIP LEARNING SYSTEM, METHOD, AND PROGRAM
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2018/087814 International Application No.: PCT/JP2016/083112
Publication Date: 17.05.2018 International Filing Date: 08.11.2016
IPC:
G06N 99/00 (2010.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99
Subject matter not provided for in other groups of this subclass
Applicants:
日本電気株式会社 NEC CORPORATION [JP/JP]; 東京都港区芝五丁目7番1号 7-1, Shiba 5-chome, Minato-ku, Tokyo 1088001, JP
Inventors:
谷本 啓 TANIMOTO Akira; JP
本橋 洋介 MOTOHASHI Yousuke; JP
藤巻 遼平 FUJIMAKI Ryohei; JP
Agent:
岩壁 冬樹 IWAKABE Fuyuki; JP
塩川 誠人 SHIOKAWA Masato; JP
Priority Data:
Title (EN) MULTI-TASK RELATIONSHIP LEARNING SYSTEM, METHOD, AND PROGRAM
(FR) SYSTÈME, PROCÉDÉ ET PROGRAMME D'APRENTISSAGE DE RELATIONS MULTITÂCHE
(JA) マルチタスク関係学習システム、方法およびプログラム
Abstract:
(EN) A multi-task relationship learning system 80 that simultaneously deduces a plurality of prediction models is provided with a learning device 81 that deduces each of the prediction models by optimizing each of the prediction models so as to minimize a function including the sum total of errors indicating consistency with data and including a normalization term for inducing sparsity related to differences between the respective prediction models.
(FR) L'invention concerne un système (80) d'apprentissage de relations multitâche qui détermine simultanément par déduction une pluralité de modèles de prédiction, ledit système étant pourvu d'un dispositif d'apprentissage (81) qui détermine par déduction chacun des modèles de prédiction par l'optimisation de chaque modèle de prédiction afin de minimiser une fonction comprenant la somme totale d'erreurs indiquant une cohérence avec des données, et comprenant un terme de normalisation pour induire une rareté liée à des différences entre les modèles de prédiction respectifs.
(JA) 複数の予測モデルを同時に推定するマルチタスク関係学習システム80であって、データとの整合を示す誤差の総和と、各予測モデル間の差に関するスパース性を誘導する正則化項とを含む関数が最小になるように各予測モデルを最適化することにより、各予測モデルを推定する学習器81を備えている。
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JP, KE, KG, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: Japanese (JA)
Filing Language: Japanese (JA)