Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2018120082) APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT FOR DEEP LEARNING
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2018/120082 International Application No.: PCT/CN2016/113651
Publication Date: 05.07.2018 International Filing Date: 30.12.2016
IPC:
G06N 3/02 (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
Applicants:
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)
Inventors:
LI, Hongyang; CN
Agent:
ZHONGZI LAW OFFICE; 7F, New Era Building, 26 Pinganli Xidajie, Xicheng District Beijing 100034, CN
Priority Data:
Title (EN) APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT FOR DEEP LEARNING
(FR) APPAREIL, PROCÉDÉ ET PRODUIT PROGRAMME D'ORDINATEUR DESTINÉS À L’APPRENTISSAGE PROFOND
Abstract:
(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
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, 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 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: English (EN)
Filing Language: English (EN)