Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020140099 - DATA AUGMENTATION IN TRANSACTION CLASSIFICATION USING A NEURAL NETWORK

Publication Number WO/2020/140099
Publication Date 02.07.2020
International Application No. PCT/US2019/068836
International Filing Date 27.12.2019
IPC
G06F 17/30 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
30Information retrieval; Database structures therefor
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
G06N 99/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99Subject matter not provided for in other groups of this subclass
CPC
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6268
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
G06K 9/627
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
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
Applicants
  • PAYPAL, INC. [US]/[US]
Inventors
  • DONG, Yanfei
Agents
  • CHEN, Tom
Priority Data
16/234,18827.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) DATA AUGMENTATION IN TRANSACTION CLASSIFICATION USING A NEURAL NETWORK
(FR) AUGMENTATION DE DONNÉES DANS UNE CLASSIFICATION DE TRANSACTIONS À L’AIDE D’UN RÉSEAU NEURONAL
Abstract
(EN)
Systems and methods for data augmentation in a neural network system includes performing a first training process, using a first training dataset on a neural network system including an autoencoder including an encoder and a decoder to generate a trained autoencoder. A trained encoder is configured to receive a first plurality of input data in an N-dimensional data space and generate a first plurality of latent variables in an M-dimensional latent space, wherein M is an integer less than N. A sampling process is performed on the first plurality of latent variables to generate a first plurality of latent variable samples. A trained decoder is used to generate a second training dataset using the first plurality of latent variable samples. The second training dataset is used to train a first classifier including a first classifier neural network model to generate a trained classifier for providing transaction classification.
(FR)
La présente invention concerne des systèmes et des procédés pour augmenter des données dans un système de réseau neuronal, comprenant la réalisation d’un premier processus d’entraînement, l’utilisation d’un premier ensemble de données d’entraînement sur un système de réseau neuronal comprenant un autocodeur comprenant un codeur et un décodeur pour générer un autocodeur entraîné. Un codeur entraîné est configuré pour recevoir une première pluralité de données d’entrée dans un espace de données à N dimensions et pour générer une première pluralité de variables latentes dans un espace latent à M dimensions, M étant un nombre entier inférieur à N. Un processus d'échantillonnage est réalisé sur la première pluralité de variables latentes pour générer une première pluralité d'échantillons de variables latentes. Un décodeur entraîné est utilisé pour générer un second ensemble de données d’entraînement à l’aide de la première pluralité d’échantillons de variables latentes. Le second ensemble de données d’entraînement est utilisé pour entraîner un premier classificateur incluant un premier modèle de réseau neuronal de classificateur pour générer un classificateur entraîné destiné à fournir une classification de transactions.
Also published as
Latest bibliographic data on file with the International Bureau