Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019030895) IDENTIFICATION/CLASSIFICATION DEVICE AND IDENTIFICATION/CLASSIFICATION METHOD
Latest bibliographic data on file with the International BureauSubmit observation

Pub. No.: WO/2019/030895 International Application No.: PCT/JP2017/029086
Publication Date: 14.02.2019 International Filing Date: 10.08.2017
IPC:
G06N 3/08 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
08
Learning methods
Applicants:
三菱電機株式会社 MITSUBISHI ELECTRIC CORPORATION [JP/JP]; 東京都千代田区丸の内二丁目7番3号 7-3, Marunouchi 2-chome, Chiyoda-ku, Tokyo 1008310, JP
Inventors:
杉原 堅也 SUGIHARA, Kenya; JP
Agent:
田澤 英昭 TAZAWA, Hideaki; JP
濱田 初音 HAMADA, Hatsune; JP
中島 成 NAKASHIMA, Nari; JP
坂元 辰哉 SAKAMOTO, Tatsuya; JP
辻岡 将昭 TSUJIOKA, Masaaki; JP
井上 和真 INOUE, Kazuma; JP
Priority Data:
Title (EN) IDENTIFICATION/CLASSIFICATION DEVICE AND IDENTIFICATION/CLASSIFICATION METHOD
(FR) DISPOSITIF ET PROCÉDÉ D'IDENTIFICATION/CLASSIFICATION
(JA) 識別分類装置および識別分類方法
Abstract:
(EN) In the present invention, a side information computation unit (110) computes side information which assists identification processing or classification processing. In a case where there is a divergence between the side information and the processing results of the identification processing or the classification processing, a multi-layer neural network (120) changes the output value of an intermediate layer (20) and executes the identification processing or the classification processing again.
(FR) Dans la présente invention, une unité de calcul d'informations annexes (110) calcule des informations annexes qui facilitent un traitement d'identification ou un traitement de classification. En cas d'existence d'une divergence entre les informations annexes et les résultats de traitement du traitement d'identification ou du traitement de classification, un réseau de neurones artificiels multicouche (120) modifie la valeur de sortie d'une couche intermédiaire (20) et exécute à nouveau le traitement d'identification ou le traitement de classification.
(JA) サイド情報算出部(110)が、識別処理または分類処理を補助するサイド情報を算出する。多層ニューラルネットワーク(120)は、識別処理または分類処理の処理結果とサイド情報との間に齟齬がある場合に、中間層(20)の出力値を変更して識別処理または分類処理を再度行う。
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, JO, JP, KE, KG, KH, 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 Organization (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (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)