Selbstüberwachtes Darstellungslernen unter Verwendung von Bootstrapping-Latentdarstellungen

Details

Veröffentlichungs-Nr.

EP4711984

Anmeldetag

4. Juni 2021

Veröffentlichung

18. März 2026

Rechtsraum

EP

IPC

G06N3/084HE ET AL., ARXIV:1512.03385

Abstract

A computer-implemented method of training a neural network. The method comprises processing a first transformed view of a training data item, e.g. an image, with a target neural network to generate a target output, processing a second transformed view of the training data item, e.g. image, with an online neural network to generate a prediction of the target output, updating parameters of the online neural network to minimize an error between the prediction of the target output and the target output, and updating parameters of the target neural network based on the parameters of the online neural network. The method can effectively train an encoder neural network without using labelled training data items, and without using a contrastive loss, i.e. without needing "negative examples" which comprise transformed views of different data items.

Anmelder

Firma

GDM Holding LLC

Land

🇺🇸 USA

Fachgebiete