Traitement en cours

Veuillez attendre...

Paramétrages

Paramétrages

Aller à Demande

1. US20180211164 - Method of training a neural network

Office États-Unis d'Amérique
Numéro de la demande 15413312
Date de la demande 23.01.2017
Numéro de publication 20180211164
Date de publication 26.07.2018
Type de publication A1
CIB
G06N 3/08
GPHYSIQUE
06CALCUL; COMPTAGE
NSYSTÈMES DE CALCULATEURS BASÉS SUR DES MODÈLES DE CALCUL SPÉCIFIQUES
3Systèmes de calculateurs basés sur des modèles biologiques
02utilisant des modèles de réseaux neuronaux
08Méthodes d'apprentissage
G06N 99/00
GPHYSIQUE
06CALCUL; COMPTAGE
NSYSTÈMES DE CALCULATEURS BASÉS SUR DES MODÈLES DE CALCUL SPÉCIFIQUES
99Matière non prévue dans les autres groupes de la présente sous-classe
CPC
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 99/005
Déposants FotoNation Limited
Inventeurs Shabab BAZRAFKAN
Joe LEMLEY
Titre
(EN) Method of training a neural network
Abrégé
(EN)

Training a target neural network comprises providing a first batch of samples of a given class to respective instances of a generative neural network, each instance providing a variant of the sample in accordance with the parameters of the generative network. Each variant produced by the generative network is compared with another sample of the class to provide a first loss function for the generative network. A second batch of samples is provided to the target neural network, at least some of the samples comprising variants produced by the generative network. A second loss function is determined for the target neural network by comparing outputs of instances of the target neural network to one or more targets for the neural network. The parameters for the target neural network are updated using the second loss function and the parameters for the generative network are updated using the first and second loss functions.