Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019045147) MEMORY OPTIMIZATION METHOD FOR APPLYING DEEP LEARNING TO PC
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2019/045147 International Application No.: PCT/KR2017/009558
Publication Date: 07.03.2019 International Filing Date: 31.08.2017
IPC:
G06K 9/62 (2006.01) ,G06K 9/46 (2006.01) ,G06K 9/00 (2006.01) ,G06N 3/08 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62
Methods or arrangements for recognition using electronic means
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36
Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46
Extraction of features or characteristics of the image
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
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:
한밭대학교 산학협력단 HANBAT NATIONAL UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION [KR/KR]; 대전시 유성구 동서대로 125 125, Dongseo-daero Yuseong-gu Daejeon 34158, KR
Inventors:
이승호 LEE, Seungho; KR
이희열 LEE, Heeyeol; KR
Agent:
이은철 LEE, Un Cheol; KR
Priority Data:
10-2017-010903429.08.2017KR
Title (EN) MEMORY OPTIMIZATION METHOD FOR APPLYING DEEP LEARNING TO PC
(FR) PROCÉDÉ D'OPTIMISATION DE MÉMOIRE PERMETTANT D'APPLIQUER UN APPRENTISSAGE PROFOND À UN PC
(KO) 딥러닝을 PC에 적용하기 위한 메모리 최적화 방법
Abstract:
(EN) A memory optimization method for applying deep learning to a PC is disclosed. The present invention comprises the steps of: (a) setting a similarity between filters so as to be a reference value or less, thereby determining a random filter set having discrimination power; (b) forming a convolution layer by using the random filter set; (c) reducing, to a number of data classes or less, a dimension of a feature vector having passed through the convolution layer; and (d) proceeding with machine learning on the dimension-reduced feature vector by using a classifier. According to the present invention, total learning time for deep learning is reduced and memory capacity and computation processing amount are reduced, and thus deep learning can also be applied to a PC.
(FR) L'invention concerne un procédé d'optimisation de mémoire permettant d'appliquer un apprentissage profond à un PC. La présente invention comprend les étapes consistant à : (a) définir une similarité entre des filtres comme étant une valeur inférieure ou égale à une valeur de référence, ce qui permet de déterminer un ensemble de filtres aléatoires ayant un pouvoir de discrimination ; (b) former une couche de convolution à l'aide de l'ensemble de filtres aléatoires ; (c) réduire, à un nombre inférieur ou égal à un nombre de classes de données, une dimension d'un vecteur de caractéristiques ayant traversé la couche de convolution ; et (d) appliquer un apprentissage machine au vecteur de caractéristiques à dimension réduite à l'aide d'un classificateur. La présente invention permet de réduire un temps d'apprentissage total d'un apprentissage profond et de réduire la capacité de mémoire et la quantité de traitement de calcul, et permet ainsi également d'appliquer un apprentissage profond à un PC.
(KO) 본 발명에서는 딥러닝을 PC에 적용하기 위한 메모리 최적화 방법을 개시하였다. 본 발명은 (a) 필터 사이의 유사율이 기준값 이하가 되도록 설정하여 분별력이 있는 랜덤 필터 세트를 결정하는 단계, (b) 상기 랜덤 필터 세트를 이용하여 컨볼루션 층을 구성하는 단계, (c) 상기 컨볼루션 층을 통과한 특징벡터의 차원을 데이터 클래스 수 이하로 축소시키는 단계, 및 (d) 상기 차원이 축소된 특징벡터를 분류기를 이용하여 기계학습을 진행하는 단계를 포함한다. 본 발명에 의하면, 전체적인 딥러닝의 학습시간을 단축시키고 메모리량과 연산처리량을 감소시키므로, 딥러닝을 PC에도 적용할 수 있다.
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, 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: Korean (KO)
Filing Language: Korean (KO)