Processing

Please wait...

Settings

Settings

Goto Application

1. KR1020220046796 - 전자 장치 및 그 제어 방법

Office
Republic of Korea
Application Number 1020200129873
Application Date 08.10.2020
Publication Number 1020220046796
Publication Date 15.04.2022
Publication Kind A
IPC
G06N 3/063
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
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
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 3/063
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 3/04
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 3/082
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
082modifying the architecture, e.g. adding or deleting nodes or connections, pruning
Applicants 삼성전자주식회사
Inventors 박배성
권세중
Agents 정홍식
김태헌
Title
(KO) 전자 장치 및 그 제어 방법
Abstract
(KO) 전자 장치가 개시된다. 본 전자 장치는 인공 지능 모델의 신경망 연산에서 압축 해제되어 이용되는 압축 데이터가 저장된 메모리, 압축 데이터를 기설정된 개수의 비트를 포함하는 그룹 단위로 순차적으로 입력받고, 적어도 두 개의 그룹의 데이터를 출력하는 시프트 레지스터, 압축 데이터의 압축 방법과 관련된 복수의 논리 회로를 통해 시프트 레지스터로부터 출력된 데이터의 압축을 해제하고, 압축 해제된 데이터를 출력하는 디코더 및 디코더로부터 출력되는 데이터로부터 신경망 연산 가능한 형태의 데이터를 획득하는 프로세서를 포함한다.
Related patent documents