Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020064988 - SCALABLE AND COMPRESSIVE NEURAL NETWORK DATA STORAGE SYSTEM

Publication Number WO/2020/064988
Publication Date 02.04.2020
International Application No. PCT/EP2019/076143
International Filing Date 27.09.2019
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
G06F 16/2272
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
20of structured data, e.g. relational data
22Indexing; Data structures therefor; Storage structures
2228Indexing structures
2272Management thereof
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
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 3/0454
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 3/0481
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 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • DEEPMIND TECHNOLOGIES LIMITED [GB]/[GB]
Inventors
  • RAE, Jack William
  • LILLICRAP, Timothy Paul
  • BARTUNOV, Sergey
Agents
  • KUNZ, Herbert
Priority Data
62/737,84027.09.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SCALABLE AND COMPRESSIVE NEURAL NETWORK DATA STORAGE SYSTEM
(FR) SYSTÈME DE STOCKAGE DE DONNÉES DE RÉSEAU NEURONAL ÉVOLUTIF ET COMPRESSIF
Abstract
(EN)
A system for compressed data storage using a neural network. The system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.
(FR)
L'invention concerne un système de stockage de données compressées à l'aide d'un réseau neuronal. Le système comprend une mémoire comprenant une pluralité d'emplacements de mémoire configurés pour stocker des données ; un réseau neuronal d'interrogation configuré pour traiter une représentation d'un élément de données d'entrée en vue de générer une interrogation ; une mémoire de données de clé immuable comprenant des données de clé servant à indexer la pluralité d'emplacements de mémoire ; un système d'adressage configuré pour traiter les données de clé et l'interrogation pour générer une pondération associée à la pluralité d'emplacements de mémoire ; un système de lecture de mémoire configuré pour générer des données de mémoire de sortie de la mémoire sur la base de la pondération générée associée à la pluralité d'emplacements de mémoire et des données stockées au niveau de la pluralité d'emplacements de mémoire ; et un système d'écriture en mémoire configuré pour écrire des données d'écriture reçues dans la mémoire sur la base de la pondération générée associée à la pluralité d'emplacements de mémoire.
Latest bibliographic data on file with the International Bureau