Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021040921 - SYSTEMS AND METHODS FOR PROVIDING VECTOR-WISE SPARSITY IN A NEURAL NETWORK

Publication Number WO/2021/040921
Publication Date 04.03.2021
International Application No. PCT/US2020/043279
International Filing Date 23.07.2020
IPC
G06F 13/16 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
13Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
14Handling requests for interconnection or transfer
16for access to memory bus
G06N 5/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
CPC
G06F 17/16
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
10Complex mathematical operations
16Matrix or vector computation ; , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
G06N 3/0481
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
0481Non-linear activation functions, e.g. sigmoids, thresholds
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
Applicants
  • ALIBABA GROUP HOLDING LIMITED
Inventors
  • ZHU, Maohua
  • ZHANG, Tao
  • GU, Zhenyu
  • XIE, Yuan
Agents
  • CAPRON, Aaron, J.
Priority Data
62/893,76829.08.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEMS AND METHODS FOR PROVIDING VECTOR-WISE SPARSITY IN A NEURAL NETWORK
(FR) SYSTÈMES ET PROCÉDÉS POUR FOURNIR UNE DISPERSION PAR VECTEURS DANS UN RÉSEAU NEURONAL
Abstract
(EN)
The present disclosure relates to systems and methods for providing vector-wise sparsity in neural networks. In some embodiments, an exemplary method for providing vector- wise sparsity in a neural network, comprises: dividing a matrix associated with the neural network into a plurality of vectors; selecting a first subset of non-zero elements from the plurality of vectors to form a pruned matrix; and outputting the pruned matrix for executing the neural network using the pruned matrix.
(FR)
La présente invention concerne des systèmes et des procédés permettant de fournir une dispersion par vecteurs dans des réseaux neuronaux. Dans certains modes de réalisation, un procédé donné à titre d'exemple pour fournir une dispersion par vecteurs dans un réseau neuronal consiste à : diviser une matrice associée au réseau neuronal en une pluralité de vecteurs; sélectionner un premier sous-ensemble d'éléments non nuls parmi la pluralité de vecteurs pour former une matrice élaguée; et produire la matrice élaguée pour exécuter le réseau neuronal à l'aide de la matrice élaguée.
Also published as
Latest bibliographic data on file with the International Bureau