Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021058466 - TRANSFORMATION OF DATA SAMPLES TO NORMAL DATA

Publication Number WO/2021/058466
Publication Date 01.04.2021
International Application No. PCT/EP2020/076404
International Filing Date 22.09.2020
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
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 3/0472
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
0472using probabilistic elements, e.g. p-rams, stochastic processors
G06N 3/088
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
088Non-supervised learning, e.g. competitive learning
Applicants
  • ANOTHER BRAIN [FR]/[FR]
Inventors
  • DEHAENE, David
  • FRIGO, Oriel
  • COMBREXELLE, Sébastien
  • ELINE, Pierre
Agents
  • MARKS & CLERK FRANCE
Priority Data
19306185.024.09.2019EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) TRANSFORMATION OF DATA SAMPLES TO NORMAL DATA
(FR) TRANSFORMATION D'ÉCHANTILLONS DE DONNÉES EN DONNÉES NORMALES
Abstract
(EN)
The invention discloses a device comprising at least one processing logic configured for: obtaining an input vector representing an input data sample; until a stop criterion is met, performing successive iterations of: using an autoencoder trained using a set of reference vectors to encode the input vector into a compressed vector, and decode the compressed vector into a reconstructed vector; calculating a reconstruction loss between the reconstructed and the input vectors, and a gradient of the reconstruction loss; updating said input vector for the subsequent iteration using said gradient.
(FR)
L'invention concerne un dispositif comprenant au moins une logique de traitement configurée pour : obtenir un vecteur d'entrée représentant un échantillon de données d'entrée ; jusqu'à ce qu'un critère d'arrêt soit satisfait, effectuer des itérations successives des opérations suivantes : utilisation d'un autocodeur entraîné à l'aide d'un ensemble de vecteurs de référence pour coder le vecteur d'entrée en un vecteur compressé, et décoder le vecteur compressé en un vecteur reconstruit ; calcul d'une perte de reconstruction entre le vecteur reconstruit et le vecteur d'entrée, et d'un gradient de la perte de reconstruction ; mise à jour dudit vecteur d'entrée pour l'itération ultérieure à l'aide dudit gradient.
Also published as
Latest bibliographic data on file with the International Bureau