이 애플리케이션의 일부 콘텐츠는 현재 사용할 수 없습니다.
이 상황이 계속되면 다음 주소로 문의하십시오피드백 및 연락
1. (WO2018120082) APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT FOR DEEP LEARNING
국제사무국에 기록된 최신 서지정보    정보 제출

공개번호: WO/2018/120082 국제출원번호: PCT/CN2016/113651
공개일: 05.07.2018 국제출원일: 30.12.2016
IPC:
G06N 3/02 (2006.01)
G SECTION G — 물리학
06
산술논리연산; 계산; 계수
N
특정 계산모델 방식의 컴퓨터시스템
3
생체모델기반 컴퓨터시스템
02
신경망 모델을 사용하는 것
출원인:
NOKIA TECHNOLOGIES OY [FI/FI]; Karaportti 3 02610 Espoo, FI
NOKIA TECHNOLOGIES (BEIJING) CO., LTD. [CN/CN]; Unit 18, Room 1001, Level 10, East Tower World Financial Center, No. 1 East Third Ring Middle Road Chaoyang District Beijing 100020, CN (LC)
발명자:
LI, Hongyang; CN
대리인:
ZHONGZI LAW OFFICE; 7F, New Era Building, 26 Pinganli Xidajie, Xicheng District Beijing 100034, CN
우선권 정보:
발명의 명칭: (EN) APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT FOR DEEP LEARNING
(FR) APPAREIL, PROCÉDÉ ET PRODUIT PROGRAMME D'ORDINATEUR DESTINÉS À L’APPRENTISSAGE PROFOND
요약서:
(EN) Apparatus (10), method, computer program product and computer readable medium are disclosed for deep learning. The apparatus (10) comprises at least one processor (11); at least one memory (12) including computer program code, the memory (12) and the computer program code configured to, working with the at least one processor (11), cause the apparatus (10) to use a two-dimensional activation function in a deep learning architecture, wherein the two-dimensional activation function comprises a first parameter representing an element to be activated and a second parameter representing the element's neighbors.
(FR) L'invention concerne un appareil (10), un procédé, un produit programme d'ordinateur et un support lisible par ordinateur destinés à l'apprentissage profond. L'appareil (10) comprend : au moins un processeur (11) ; et au moins une mémoire (12) incluant un code de programme d'ordinateur, la mémoire (12) et le code de programme d'ordinateur étant configurés pour, en association avec le ou les processeurs (11), amener l'appareil (10) à utiliser une fonction d'activation bidimensionnelle dans une architecture d'apprentissage profond, la fonction d'activation bidimensionnelle comprenant un premier paramètre qui représente un élément à activer et un second paramètre qui représente les voisins de l'élément.
front page image
지정국: 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, 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
아프리카지역 지식재산권기구(ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
유라시아 특허청 (AM, AZ, BY, KG, KZ, RU, TJ, TM)
유럽 특허청(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)
공개언어: 영어 (EN)
출원언어: 영어 (EN)