Traitement en cours

Veuillez attendre...

Paramétrages

Paramétrages

Aller à Demande

1. CN111758104 - METHOD FOR OPTIMIZING NEURAL NETWORK PARAMETER APPROPRIATE FOR HARDWARE IMPLEMENTATION, NEURAL NETWORK OPERATION METHOD, AND APPARATUS THEREFOR

Office
Chine
Numéro de la demande 201980007377.0
Date de la demande 18.07.2019
Numéro de publication 111758104
Date de publication 09.10.2020
Type de publication A
CIB
G06N 3/04
GPHYSIQUE
06CALCUL; COMPTAGE
NSYSTÈMES DE CALCULATEURS BASÉS SUR DES MODÈLES DE CALCUL SPÉCIFIQUES
3Systèmes de calculateurs basés sur des modèles biologiques
02utilisant des modèles de réseaux neuronaux
04Architecture, p.ex. topologie d'interconnexion
G06N 3/063
GPHYSIQUE
06CALCUL; COMPTAGE
NSYSTÈMES DE CALCULATEURS BASÉS SUR DES MODÈLES DE CALCUL SPÉCIFIQUES
3Systèmes de calculateurs basés sur des modèles biologiques
02utilisant des modèles de réseaux neuronaux
06Réalisation physique, c. à d. mise en oeuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurones
063utilisant des moyens électroniques
CPC
G06N 3/0454
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
0454using a combination of multiple neural nets
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 3/082
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
G06N 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
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
Déposants DEEPER-I CO INC
深爱智能科技有限公司
Inventeurs LEE SANG-HUN
李相宪
KIM MYUNG-KYUM
金明谦
KIM JOO-HYUK
金周赫
Mandataires 北京青松知识产权代理事务所(特殊普通合伙) 11384
Données relatives à la priorité 1020190011516 29.01.2019 KR
1020190011516 29.01.2019 KR
Titre
(EN) METHOD FOR OPTIMIZING NEURAL NETWORK PARAMETER APPROPRIATE FOR HARDWARE IMPLEMENTATION, NEURAL NETWORK OPERATION METHOD, AND APPARATUS THEREFOR
(ZH) 适合于硬件实现的神经网络参数优化方法、神经网络计算方法和装置
Abrégé
(EN)
The present invention relates to a method for optimizing a neural network parameter appropriate for hardware implementation, a neural network operation method, and an apparatus therefor. The method for optimizing a neural network parameter appropriate for hardware implementation according to the present invention may comprise the steps of: performing type conversion of an existing parameter of a neural network into a size parameter having a single value per channel and a code parameter; and branching out the type-converted size parameter to generate an optimized parameter. Accordingly, the present invention can provide a neural network parameter optimization method, a neural network calculation method, and an apparatus therefor, wherein large operational quantities and parameters which a convolution neural network has are effectively optimized for hardware implementation so that a minimum loss in accuracy and a maximum operational speed can be obtained.

(ZH)
本发明涉及一种适合于硬件实现的神经网络参数优化方法、神经网络计算方法和装置。根据本发明的适合硬件实现的神经网络参数优化方法可以包括:将神经网络中的现有参数变换成符号化参数和对于每个通道具有单个值的大小参数;再通过剪枝已变换的大小参数而生成优化参数。因此,本发明提供通过在硬件实现中有效地优化卷积神经网络的大量计算及其参数而获得最小的精度损失和最快的计算速度的神经网络参数优化方法、神经网络计算方法及其装置。