Processing

Please wait...

Settings

Settings

Goto Application

1. EP3467717 - MACHINE LEARNING SYSTEM

Office European Patent Office
Application Number 17275185
Application Date 21.11.2017
Publication Number 3467717
Publication Date 10.04.2019
Publication Kind A1
IPC
G06N 3/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
G06N 3/04
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
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 7/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
7Computer systems based on specific mathematical models
CPC
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 3/0454
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 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 7/005
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
7Computer systems based on specific mathematical models
005Probabilistic networks
Applicants PROWLER IO LTD
Inventors TUKIAINEN ALEKSI
KIM DONGHO
NICHOLSON THOMAS
TOMCZAK MARCIN
MUNOZ DE COTE FLORES LUNA JOSE ENRIQUE
FERGUSON NEIL
ELEFTHERIADIS STEFANOS
SEPPA JUHA
BEATTIE DAVID
JENNINGS JOEL
HENSMAN JAMES
LEIBFRIED FELIX
GRAU-MOYA JORDI
JOHN SEBASTIAN
BOU-AMMAR HAITHAM
VRANCX PETER
Designated States
Priority Data 20170100448 04.10.2017 GR
Title
(DE) MASCHINENLERNSYSTEM
(EN) MACHINE LEARNING SYSTEM
(FR) SYSTÈME D'APPRENTISSAGE PAR MACHINE
Abstract
(EN)
There is described a machine learning system comprising a first subsystem and a second subsystem remote from the first subsystem. The first subsystem comprises an environment having multiple possible states, the environment being arranged to output a state signal comprising data indicative of the state of the environment at a discrete time and to receive an action signal operable to cause a change of state, and a decision making subsystem comprising one or more agents, each agent being configured to generate an action signal dependent on the data conveyed by the received state signal and a policy associated with that agent, the decision making subsystem being further arranged to generate experience data dependent on data conveyed by the state signal and the action signal. The first subsystem also includes a first network interface configured to send said experience data to the second subsystem and to receive policy data from the second subsystem. The second subsystem comprises: a second network interface configured to receive experience data from the first subsystem and send policy data to the first subsystem; and a learning routine configured to process said received experience data to generate said policy data, dependent on the experience data, for updating one or more policies associated with the one or more agents. The decision making subsystem is operable to update the one or more policies associated with the one or more agents in accordance with policy data received from the second subsystem.