Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022075613 - ELECTRONIC DEVICE FOR DECOMPRESSING COMPRESSED ARTIFICIAL INTELLIGENCE MODEL, AND CONTROL METHOD THEREFOR

Publication Number WO/2022/075613
Publication Date 14.04.2022
International Application No. PCT/KR2021/012371
International Filing Date 10.09.2021
IPC
G06N 3/063 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
G06N 3/04 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
G06N 3/063
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • 삼성전자주식회사 SAMSUNG ELECTRONICS CO., LTD. [KR]/[KR]
Inventors
  • 박배성 PARK, Baeseong
  • 권세중 KWON, Sejung
Agents
  • 김태헌 KIM, Tae-hun
  • 정홍식 JEONG, Hong-sik
Priority Data
10-2020-012987308.10.2020KR
Publication Language Korean (ko)
Filing Language Korean (KO)
Designated States
Title
(EN) ELECTRONIC DEVICE FOR DECOMPRESSING COMPRESSED ARTIFICIAL INTELLIGENCE MODEL, AND CONTROL METHOD THEREFOR
(FR) DISPOSITIF ÉLECTRONIQUE POUR LA DÉCOMPRESSION D'UN MODÈLE D'INTELLIGENCE ARTIFICIELLE COMPRESSÉ, ET SON PROCÉDÉ DE COMMANDE
(KO) 압축된 인공 지능 모델을 압축 해제하기 위한 전자 장치 및 그 제어 방법
Abstract
(EN) An electronic device comprises: a memory that stores therein compressed data that is decompressed for neural network computation of an artificial intelligence model; a shift register that sequentially receives the compressed data in group units and outputs the compressed data of at least two groups; a decoder configured to decompress the compressed data of the at least two groups, and obtain the decompressed data; and a processor that obtains the decompressed data in a neural network operable form.
(FR) Un dispositif électronique comprend : une mémoire dans laquelle sont stockées des données compressées qui seront décompressées pour le calcul d'un réseau de neurones d'un modèle d'intelligence artificielle ; un registre à décalage qui reçoit séquentiellement les données compressées par unités de groupe et délivre en sortie les données compressées d'au moins deux groupes ; un décodeur configuré pour décompresser les données compressées desdits au moins deux groupes, et obtenir les données décompressées ; et un processeur qui obtient les données décompressées sous une forme utilisable par un réseau de neurones.
(KO) 전자 장치는 인공 지능 모델의 신경망 연산을 위해 압축 해제되는 압축 데이터가 저장된 메모리, 압축 데이터를 그룹 단위로 순차적으로 입력받고, 적어도 두 개의 그룹의 압축 데이터를 출력하는 시프트 레지스터, 적어도 두 개의 그룹의 압축 데이터를 압축 해제하고, 압축 해제된 데이터를 획득하도록 구성된 디코더 및 신경망 연산 가능한 형태의 압축 해제된 데이터를 획득하는 프로세서를 포함한다.
Related patent documents
Latest bibliographic data on file with the International Bureau