FR3119695B1 - Device and method for training a decision support system - Google Patents

Device and method for training a decision support system Download PDF

Info

Publication number
FR3119695B1
FR3119695B1 FR2101136A FR2101136A FR3119695B1 FR 3119695 B1 FR3119695 B1 FR 3119695B1 FR 2101136 A FR2101136 A FR 2101136A FR 2101136 A FR2101136 A FR 2101136A FR 3119695 B1 FR3119695 B1 FR 3119695B1
Authority
FR
France
Prior art keywords
unit
data vector
units
selection
input data
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
FR2101136A
Other languages
French (fr)
Other versions
FR3119695A1 (en
Inventor
Andrea Ancora
Matthieu Da-Silva-Filarder
Maxime Derome
Pietro Michiardi
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.)
Renault SAS
Original Assignee
Renault 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 Renault SAS filed Critical Renault SAS
Priority to FR2101136A priority Critical patent/FR3119695B1/en
Publication of FR3119695A1 publication Critical patent/FR3119695A1/en
Application granted granted Critical
Publication of FR3119695B1 publication Critical patent/FR3119695B1/en
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
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • 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

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)
  • Error Detection And Correction (AREA)
  • Control Of Ac Motors In General (AREA)

Abstract

Les modes de réalisation de l’invention fournissent un dispositif d’entraînement (100) configuré pour recevoir des blocs de données d’entrée, le dispositif (100) peut comprendre : une pluralité d’unités d’encodage (101-i), chaque unité d’encodage (101-i) étant configurée pour déterminer un vecteur de données représentatif du bloc de données d’entrée reçu ;une pluralité d’unités de sélection (102-i), chaque unité de sélection étant configurée pour annuler un nombre N supérieur ou égal à zéro d’éléments du vecteur de données en appliquant un masque de sélection au vecteur de données, ce qui fournit un vecteur de données mis à jour ; une unité de fusion (103) configurée pour déterminer une représentation commune à partir des vecteurs de données mis à jour ;une pluralité d’unités de reconstruction (104-i), chaque unité de reconstruction (104-i) étant configurée pour déterminer une représentation reconstruite du bloc de données d’entrée reçu. Figure pour l’abrégé : Fig. 1Embodiments of the invention provide a drive device (100) configured to receive blocks of input data, the device (100) may comprise: a plurality of encoding units (101-i), each encoding unit (101-i) being configured to determine a data vector representative of the received input data block; a plurality of selection units (102-i), each selection unit being configured to cancel a number N greater than or equal to zero of elements of the data vector by applying a selection mask to the data vector, which provides an updated data vector; a fusion unit (103) configured to determine a common representation from the updated data vectors; a plurality of reconstruction units (104-i), each reconstruction unit (104-i) being configured to determine a reconstructed representation of the received input data block. Figure for abstract: Fig. 1

FR2101136A 2021-02-05 2021-02-05 Device and method for training a decision support system Active FR3119695B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
FR2101136A FR3119695B1 (en) 2021-02-05 2021-02-05 Device and method for training a decision support system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR2101136A FR3119695B1 (en) 2021-02-05 2021-02-05 Device and method for training a decision support system
FR2101136 2021-02-05

Publications (2)

Publication Number Publication Date
FR3119695A1 FR3119695A1 (en) 2022-08-12
FR3119695B1 true FR3119695B1 (en) 2024-03-22

Family

ID=75746810

Family Applications (1)

Application Number Title Priority Date Filing Date
FR2101136A Active FR3119695B1 (en) 2021-02-05 2021-02-05 Device and method for training a decision support system

Country Status (1)

Country Link
FR (1) FR3119695B1 (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11214268B2 (en) * 2018-12-28 2022-01-04 Intel Corporation Methods and apparatus for unsupervised multimodal anomaly detection for autonomous vehicles
US20200356835A1 (en) * 2019-05-09 2020-11-12 LGN Innovations Limited Sensor-Action Fusion System for Optimising Sensor Measurement Collection from Multiple Sensors

Also Published As

Publication number Publication date
FR3119695A1 (en) 2022-08-12

Similar Documents

Publication Publication Date Title
CN104365095B (en) Method and apparatus for being encoded to the selected space segment of video flowing
US20230154630A1 (en) Realizing private and practical pharmacological collaboration using a neural network architecture configured for reduced computation overhead
ES2171716T3 (en) COMMUNICATION SYSTEM THAT USES SELECTED REPEATED DATA.
DK2101430T3 (en) Method and apparatus for transmitting control information in a wireless communication system
FR3119695B1 (en) Device and method for training a decision support system
GB0209780D0 (en) Method of encoding data for decoding data from and constraining a neural network
MY195878A (en) System And Method For Training Neural Networks
Peralta et al. Multiobjective optimization for railway maintenance plans
CN102823249A (en) Motion vector predictive encoding method, motion vector predictive decoding method, moving picture encoding apparatus, moving picture decoding apparatus, and programs thereof
Ng et al. Achieving state‐of‐the‐art ICT connectivity in developing countries: The Azerbaijan model of Technology Leapfrogging
Bababeik et al. Developing a train timetable according to track maintenance plans: A stochastic optimization of buffer time schedules
Cassidy Occupational attainment of natives and immigrants: A cross-cohort analysis
FR3041199B1 (en) Dual frequency elements for wellbore telecommunications
FI103551B1 (en) Method and apparatus for testing and controlling majority voting
Giri Dimensions of digital Nepal framework and appropriate roadmap
EA202192620A1 (en) DYNAMIC VIRTUAL COPIES OF PRODUCTION FACILITIES
Lambelet et al. The influence of politicization on the implementation of developer obligations in a federalist country: Evidence from Switzerland 1
الهادي et al. Weka–GUI Way to Learn Machine Learning
Mahmood et al. Implementation and evaluation of “I-Guide,” a pilot near-peer Internal Medicine mentorship program
FR3082018B1 (en) DEVICE AND METHOD FOR OPTIMIZING THE USE OVER TIME OF THE RESOURCES OF A COMPUTER INFRASTRUCTURE
Kubiriba et al. Scaling out control of banana xanthomonas wilt from community to regional level: A case from Ugandas largest banana growing region
FR3101325B1 (en) UNDERWATER EXPLORATION SYSTEM INCLUDING A FLEET OF DRONES
FR3108423B1 (en) Decision support device and method for an artificial cognitive system
Yang et al. Long-term maintenance optimization for integrated mining operations
CN109298836B (en) Method, apparatus and storage medium for processing data

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20220812

PLFP Fee payment

Year of fee payment: 3

CA Change of address

Effective date: 20230512

PLFP Fee payment

Year of fee payment: 4