Ausgleichen von Multitask-Lernen durch Bedingten oder Parallelen Stapelabbau

Details

Veröffentlichungs-Nr.

EP4095760

Aktenzeichen

EP21175738

Anmeldetag

25. Mai 2021

Veröffentlichung

21. Februar 2024

Erteilung

21. Februar 2024

Rechtsraum

EP

IPC

G06N3/08G06T7/00G06V10/774G06V10/82

Abstract

Methods, systems and computer program products, for training a multitask neural network. First and second datasets are provided, containing samples for a first task and a second task, respectively. First and second batch miners are provided for mining samples from the first and second datasets. First and second costs for completing the first and second tasks, respectively, are assessed using a first sample mined by the first batch miner from the first dataset and a second sample mined by the second batch miner from the second dataset. When the first or second cost, respectively, falls within a range delimited by lower and upper thresholds, the is added to a first or second batch, respectively. When a termination condition is reached for either the first or second batch, the first or the second batch is used to update the neural network.

Anmelder

Firma

Axis AB

Land

🇸🇪 Schweden

Fachgebiete