Feedback
Settings

Settings

Goto Application

1. WO2020153651 - NEURAL NETWORK SIMULATOR AND NEURAL NETWORK SIMULATION LEARNING SYSTEM

Submit observation
PermaLink
Publication Number WO/2020/153651
Publication Date 30.07.2020
International Application No. PCT/KR2020/000707
International Filing Date 15.01.2020
IPC
G06N 3/063 2006.01
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
H01L 43/08 2006.01
HELECTRICITY
01BASIC ELECTRIC ELEMENTS
LSEMICONDUCTOR DEVICES; ELECTRIC SOLID STATE DEVICES NOT OTHERWISE PROVIDED FOR
43Devices using galvano-magnetic or similar magnetic effects; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof
08Magnetic-field-controlled resistors
G11C 11/54 2006.01
GPHYSICS
11INFORMATION STORAGE
CSTATIC STORES
11Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
54using elements simulating biological cells, e.g. neuron
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
G11C 11/54
GPHYSICS
11INFORMATION STORAGE
CSTATIC STORES
11Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
54using elements simulating biological cells, e.g. neuron
H01L 43/08
HELECTRICITY
01BASIC ELECTRIC ELEMENTS
LSEMICONDUCTOR DEVICES; ELECTRIC SOLID STATE DEVICES NOT OTHERWISE PROVIDED FOR
43Devices using galvano-magnetic or similar magnetic effects; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof
08Magnetic-field-controlled resistors
Applicants
  • 한양대학교 산학협력단 IUCF-HYU(INDUSTRY-UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY) [KR]/[KR]
Inventors
  • 박완준 PARK, Wanjun
Agents
  • 박상열 PARK, Sangyoul
Priority Data
10-2019-000750321.01.2019KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) NEURAL NETWORK SIMULATOR AND NEURAL NETWORK SIMULATION LEARNING SYSTEM
(FR) SIMULATEUR DE RÉSEAU NEURONAL ET SYSTÈME D'APPRENTISSAGE DE SIMULATION DE RÉSEAU NEURONAL
(KO) 신경망 모사 소자 및 신경망 모사 학습 시스템
front page image
Abstract
(EN)
A neural network simulator according to an embodiment of the present invention may comprise: a first neuron simulator including a first magnetic tunnel junction structure for outputting a first output stream in which a low level and a high level are mixed at a first ratio; and a synapse simulator which receives the first output stream and a second output stream in which a low level and a high level are mixed at a second ratio, and has electrical conductivity properties changing according to the difference between the first ratio and the second ratio.
(FR)
La présente invention concerne, selon un mode de réalisation, un simulateur de réseau neuronal pouvant comprendre : un premier simulateur neuronal comprenant une première structure de jonction de tunnel magnétique pour délivrer un premier flux de sortie dans lequel un niveau bas et un niveau haut sont mélangés selon un premier rapport ; et un simulateur de synapses qui reçoit le premier flux de sortie et un second flux de sortie dans lequel un niveau bas et un niveau élevé sont mélangés selon un second rapport, et dont des propriétés de conductivité électrique changent en fonction de la différence entre le premier rapport et le second rapport.
(KO)
본 발명의 일 실시 예에 따른 신경망 모사 소자는 로우 레벨과 하이 레벨이 제1 비율로 혼재된 제1 출력 스트림을 출력하는 제1 자기터널접합구조체를 포함하는 제1 뉴런 모사 소자 및 상기 제1 출력 스트림과, 로우 레벨과 하이 레벨이 제2 비율로 혼재된 제2 출력 스트림을 각각 제공받고, 상기 제1 비율과 상기 제2 비율의 차이에 따라 전기 전도도 특성이 가변하는 시냅스 모사 소자를 포함하여 이루어질 수 있다.
Also published as
KR1020200090450
Latest bibliographic data on file with the International Bureau
# -