Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020111356 - SPIKING NEURAL NETWORK DEVICE AND INTELLIGENT DEVICE INCLUDING SAME

Publication Number WO/2020/111356
Publication Date 04.06.2020
International Application No. PCT/KR2018/015188
International Filing Date 03.12.2018
IPC
G06N 3/04 2006.01
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 2006.01
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 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • 전자부품연구원 KOREA ELECTRONICS TECHNOLOGY INSTITUTE [KR]/[KR]
Inventors
  • 황태호 HWANG, Taeho
  • 김병수 KIM, Byungsoo
  • 권진산 KWON, Jinsan
Agents
  • 박종한 PARK, Chonghan
Priority Data
10-2018-014741526.11.2018KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) SPIKING NEURAL NETWORK DEVICE AND INTELLIGENT DEVICE INCLUDING SAME
(FR) DISPOSITIF À RÉSEAU NEURONAL IMPULSIONNEL ET DISPOSITIF INTELLIGENT CONTENANT CELUI-CI
(KO) 스파이킹 뉴럴 네트워크 장치 및 이를 포함하는 지능형 장치
Abstract
(EN)
Disclosed are a spiking neural network device and an intelligent device including same. The spiking neural network device according to the present invention includes: a pre-processing unit for receiving multichannel data, filtering and normalizing the received data and converting the filtered and normalized data to multidimensional data, and extracting feature points of the converted multidimensional data; and a spiking neural network unit which is designed to allocate one neuron to each piece of the multidimensional data from which the feature points have been extracted and generate spike signals according to the intensities of signals, connects each of the neurons, allocates one synapse between each of the connected neurons, sends out the spike signals by comparing a preset threshold and the sum of the values of the synapses from which the spike signals have been generated among the synapses, and groups the sent out spike signals to classify and cluster the same.
(FR)
L'invention concerne un dispositif à réseau neuronal impulsionnel et un dispositif intelligent contenant celui-ci. Le dispositif à réseau neuronal impulsionnel selon la présente invention comprend : une unité de prétraitement permettant de recevoir des données à multiples canaux, filtrer et normaliser les données reçues et convertir les données filtrées et normalisées en données multidimensionnelles, et extraire des points caractéristiques des données multidimensionnelles converties ; et une unité de réseau neuronal impulsionnel qui est conçue pour attribuer un neurone à chacune des données multidimensionnelles à partir desquelles les points caractéristiques ont été extraits et produire des signaux impulsionnels selon les intensités de signaux, connecte chacun des neurones, attribue une synapse entre chacun des neurones connectés, envoie les signaux impulsionnels en comparant un seuil prédéfini et la somme des valeurs des synapses à partir desquelles les signaux impulsionnels ont été produits parmi les synapses, et regroupe les signaux impulsionnels envoyés pour classifier et regrouper ceux-ci.
(KO)
본 발명은 스파이킹 뉴럴 네트워크 장치 및 이를 포함하는 지능형 장치이 개시된다. 본 발명의 스파이킹 뉴럴 네트워크 장치는 다채널의 데이터를 수신하고, 상기 수신된 데이터를 필터링 및 표준화(normalization)하여 다차원 데이터로 변환하며, 상기 변환된 다차원 데이터의 특징점을 추출하는 전처리부 및 특징점이 추출된 다차원 데이터마다 하나의 뉴런을 할당하여 신호의 강도에 따라 스파이크 신호를 생성하도록 설계하고, 각 뉴런을 연결하며, 연결된 뉴런 간에 하나의 시냅스를 할당하고, 시냅스 중 스파이크 신호가 발생된 시냅스의 값에 대한 합산 값과 기 설정된 문턱치 값을 비교하여 스파이크 신호를 내보내며, 내보내진 스파이크 신호를 그룹핑하여 분류하고, 군집화하는 스파이킹 뉴럴 네트워크부를 포함한다.
Also published as
Latest bibliographic data on file with the International Bureau