Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Saturday 31.10.2020 at 7:00 AM CET
Settings

Settings

Goto Application

1. WO2020182989 - SCHEDULING COMPUTATION GRAPHS USING NEURAL NETWORKS

Publication Number WO/2020/182989
Publication Date 17.09.2020
International Application No. PCT/EP2020/056883
International Filing Date 13.03.2020
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
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
G06F 9/50 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
46Multiprogramming arrangements
50Allocation of resources, e.g. of the central processing unit
G06N 3/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
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 3/12 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
12using genetic models
CPC
G06F 9/5066
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
46Multiprogramming arrangements
50Allocation of resources, e.g. of the central processing unit [CPU]
5061Partitioning or combining of resources
5066Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
G06K 9/6262
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6262Validation, performance evaluation or active pattern learning techniques
G06K 9/6296
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6296Graphical models, e.g. Bayesian networks
G06N 20/10
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
10using kernel methods, e.g. support vector machines [SVM]
G06N 3/006
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
004Artificial life, i.e. computers simulating life
006based on simulated virtual individual or collective life forms, e.g. single "avatar", social simulations, virtual worlds or particle swarm optimisation
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
Applicants
  • DEEPMIND TECHNOLOGIES LIMITED [GB]/[GB]
Inventors
  • LI, Yujia
  • NAIR, Vinod
  • GIL, Felix Axel
  • PALIWAL, Aditya
  • LUBIN, Miles C.
Agents
  • KUNZ, Herbert
Priority Data
62/817,97113.03.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SCHEDULING COMPUTATION GRAPHS USING NEURAL NETWORKS
(FR) PLANIFICATION DE GRAPHES DE CALCUL À L'AIDE DE RÉSEAUX NEURONAUX
Abstract
(EN)
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a schedule for a computation graph. One of the methods includes obtaining data representing an input computation graph; processing the data representing the input computation graph using a graph neural network to generate one or more instance-specific proposal distributions; and generating a schedule for the input computation graph by performing an optimization algorithm in accordance with the one or more instance-specific proposal distributions.
(FR)
La présente invention concerne des procédés, des systèmes et un appareil, y compris des programmes informatiques codés sur des supports d'informations informatiques, permettant de générer une planification pour un graphe de calcul. L'un des procédés consiste à obtenir des données représentant un graphe de calcul d'entrée; à traiter des données représentant le graphe de calcul d'entrée à l'aide d'un réseau neuronal graphique pour générer une ou plusieurs distributions de proposition spécifiques d'instance; et à générer une planification pour le graphe de calcul d'entrée par réalisation d'un algorithme d'optimisation en fonction de la ou des distributions de propositions spécifiques d'une instance.
Latest bibliographic data on file with the International Bureau