Processing

Please wait...

Settings

Settings

Goto Application

1. WO2018136697 - DYNAMIC-LENGTH STATEFUL TENSOR ARRAY

Publication Number WO/2018/136697
Publication Date 26.07.2018
International Application No. PCT/US2018/014349
International Filing Date 19.01.2018
IPC
G06N 3/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
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
G06F 16/9024
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
90Details of database functions independent of the retrieved data types
901Indexing; Data structures therefor; Storage structures
9024Graphs; Linked lists
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 3/0445
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
0445Feedback networks, e.g. hopfield nets, associative networks
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 3/105
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
10Simulation on general purpose computers
105Shells for specifying net layout
Applicants
  • GOOGLE LLC [US]/[US]
Inventors
  • BREVDO, Eugene
Agents
  • GROSVENOR, Stephanie, D.
Priority Data
15/410,64319.01.2017US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) DYNAMIC-LENGTH STATEFUL TENSOR ARRAY
(FR) RÉSEAU DE TENSEURS À ÉTATS À LONGUEUR DYNAMIQUE
Abstract
(EN)
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for efficiently processing dynamic length tensors of a machine learning model represented by a computational graph. A program is received that specifies a dynamic, iterative computation that can be performed on input data for processing by a machine learning model. A directed computational graph representing the machine learning model is generated that specifies the dynamic, iterative computation as one or more operations using a tensor array object. Input is received for processing by the machine learning model and the directed computational graph representation of the machine learning model is executed with the received input to obtain output.
(FR)
La présente invention concerne des procédés, des systèmes et un appareil, y compris des programmes informatiques codés sur des supports de stockage informatiques, qui permettent de traiter efficacement des tenseurs à longueur dynamique d'un modèle d'apprentissage machine représenté par un graphe de calcul. Un programme est reçu, lequel spécifie un calcul itératif dynamique qui peut être effectué sur des données d'entrée pour un traitement par un modèle d'apprentissage machine. Un graphe de calcul orienté représentant le modèle d'apprentissage machine est généré, lequel spécifie le calcul itératif dynamique sous la forme d'une ou plusieurs opérations à l'aide d'un objet de réseau de tenseurs. Une entrée est reçue pour un traitement par le modèle d'apprentissage machine, et la représentation par graphe de calcul orienté du modèle d'apprentissage machine est exécutée avec l'entrée reçue pour obtenir une sortie.
Also published as
Latest bibliographic data on file with the International Bureau