FR3102277B1 - Préparation de jeu de données pour un apprentissage automatique multi-agents - Google Patents

Préparation de jeu de données pour un apprentissage automatique multi-agents Download PDF

Info

Publication number
FR3102277B1
FR3102277B1 FR1911592A FR1911592A FR3102277B1 FR 3102277 B1 FR3102277 B1 FR 3102277B1 FR 1911592 A FR1911592 A FR 1911592A FR 1911592 A FR1911592 A FR 1911592A FR 3102277 B1 FR3102277 B1 FR 3102277B1
Authority
FR
France
Prior art keywords
machine learning
agent
datasets
preparing
agent machine
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
FR1911592A
Other languages
English (en)
Other versions
FR3102277A1 (fr
Inventor
Jonathan Bonnet
Florent Pajot
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Continental Automotive Technologies GmbH
Original Assignee
Continental Automotive France SAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Continental Automotive France SAS filed Critical Continental Automotive France SAS
Priority to FR1911592A priority Critical patent/FR3102277B1/fr
Publication of FR3102277A1 publication Critical patent/FR3102277A1/fr
Application granted granted Critical
Publication of FR3102277B1 publication Critical patent/FR3102277B1/fr
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/043—Distributed expert systems; Blackboards

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Machine Translation (AREA)
  • Feedback Control In General (AREA)

Abstract

L’invention a pour objet des systèmes informatiques (100) et procédés (200) pour l’apprentissage automatique prédictif d’au moins une première caractéristique physique d’un système complexe du type électronique et/ou mécanique, tel un véhicule routier. Le principe général de l’invention est basé sur l’utilisation du paradigme des systèmes multi-agents dans la mise en œuvre de l’apprentissage automatique (« machine learning », en anglais) de manière décentralisée et ascendante. En pratique, l’invention recourt à l’approche des systèmes multi-agents adaptatifs coopératifs (« Adaptive Multi-Agent System » ou AMAS en anglais). Dans ce cadre, la présente invention concerne particulièrement la préparation du jeu de données d’apprentissage à répartir entre les différents agents. Figure 1
FR1911592A 2019-10-17 2019-10-17 Préparation de jeu de données pour un apprentissage automatique multi-agents Active FR3102277B1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
FR1911592A FR3102277B1 (fr) 2019-10-17 2019-10-17 Préparation de jeu de données pour un apprentissage automatique multi-agents

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1911592A FR3102277B1 (fr) 2019-10-17 2019-10-17 Préparation de jeu de données pour un apprentissage automatique multi-agents
FR1911592 2019-10-17

Publications (2)

Publication Number Publication Date
FR3102277A1 FR3102277A1 (fr) 2021-04-23
FR3102277B1 true FR3102277B1 (fr) 2021-09-17

Family

ID=69810956

Family Applications (1)

Application Number Title Priority Date Filing Date
FR1911592A Active FR3102277B1 (fr) 2019-10-17 2019-10-17 Préparation de jeu de données pour un apprentissage automatique multi-agents

Country Status (1)

Country Link
FR (1) FR3102277B1 (fr)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016160005A1 (fr) * 2015-04-01 2016-10-06 Landmark Graphics Corporation Génération de modèles pour prédiction en temps réel de taux de pénétration
WO2018212918A1 (fr) * 2017-05-18 2018-11-22 Microsoft Technology Licensing, Llc Architecture de récompense hybride pour apprentissage par renforcement

Also Published As

Publication number Publication date
FR3102277A1 (fr) 2021-04-23

Similar Documents

Publication Publication Date Title
SG11201909249QA (en) Method and device for writing service data in block chain system
US10614488B2 (en) Digital sign advertisement selection based on mobile device activity
MX2009000589A (es) Procesamiento de datos a traves de bases de datos muy grandes.
US20040230565A1 (en) System and method for obtaining alternate contact information
WO2004104739A3 (fr) Procede et systeme de reduction de la latence des informations dans une entreprise commerciale
US20090157705A1 (en) Systems, methods and computer products for name disambiguation by using private/global directories, and communication contexts
WO2006008733A3 (fr) Procede de determination de quasi duplicata d'objets
SG165369A1 (en) Electronic vehicle identification
ATE395413T1 (de) Antikörperkategorisierung auf der grundlage von bindungseigenschaften
WO2005024043A3 (fr) Procedes d'identification, de diagnostic et de prediction pour la survie des lymphomes
US10733220B2 (en) Document relevance determination for a corpus
WO2006004670A3 (fr) Procédé et système de gestion de données
WO2007019311A3 (fr) Systemes et procedes pour trouver des documents pertinents en analysant des etiquettes
CN102624703A (zh) 统一资源定位符url的过滤方法及装置
US7302681B2 (en) Method and system for customized information handling system support updates
US20210097197A1 (en) Systems and methods for detecting personally identifiable information
FR3102277B1 (fr) Préparation de jeu de données pour un apprentissage automatique multi-agents
DK1455959T3 (da) Fremgangsmåde og anordning til posthandtering
US9652627B2 (en) Probabilistic surfacing of potentially sensitive identifiers
FR3102260B1 (fr) Apprentissage automatique multi-agents.
US11314797B2 (en) Data de-identification apparatus and method
US10601785B2 (en) Obscuring internet searches from external web service providers
CN106156000A (zh) 基于求交算法的搜索方法及搜索系统
FR3109662B1 (fr) Procédé et système informatique de suivi de trafic routier
US20240004904A1 (en) Edge computing data reproduction and filtering gatekeeper

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20210423

PLFP Fee payment

Year of fee payment: 3

PLFP Fee payment

Year of fee payment: 4

TP Transmission of property

Owner name: CONTINENTAL AUTOMOTIVE TECHNOLOGIES GMBH, DE

Effective date: 20230807

PLFP Fee payment

Year of fee payment: 5