公开(公告)号：US20210089872A1

公开(公告)日：2021-03-25

申请号：US16891697

申请日：2020-06-03

Applicant: Nokia Technologies Oy

Inventor： Shaoduo GAN ,  Akhil MATHUR ,  Anton ISOPOUSSU

IPC: G06N3/063 ,  G06N3/08 ,  H03M7/30

Abstract: An apparatus, method and computer program is described comprising: initialising weights of a target encoder based on a source encoder; initialising weights of a target discriminator associated with the target encoder such that the target discriminator is initialised to match a source discriminator associated with the source encoder; applying some of a target data set to the target encoder to generate target encoder outputs; applying the target encoder outputs to the target discriminator to generate a first local loss function output; training the target encoder to seek to increase the first local loss function output; training the target discriminator to seek to decrease the first local loss function output; and synchronising weights of the target discriminator and the source discriminator.

公开(公告)号：US20200027442A1

公开(公告)日：2020-01-23

申请号：US16513212

申请日：2019-07-16

Applicant: Nokia Technologies Oy

Inventor： Akhil MATHUR ,  Anton ISOPOUSSU ,  Nicholas LANE ,  Fahim KAWSAR

IPC: G10L15/01 ,  G06N20/00 ,  G06N3/08 ,  G10L21/02 ,  G10L15/06 ,  G10L15/18 ,  G10L15/16

Abstract: An apparatus comprising means for: using a generative neural network, trained to translate first sensor data to simulated second sensor data, to translate input first sensor data from a first sensor to simulated second sensor data; and providing the simulated second sensor data to a different, specific-task, machine-learning model for processing at least second sensor data.