公开(公告)号：US20240013046A1

公开(公告)日：2024-01-11

申请号：US18247200

申请日：2021-09-02

Applicant: Nokia Technologies Oy

Inventor： Nam LE ,  Francesco CRICRÌ ,  Honglei ZHANG ,  Hamed REZAZADEGAN TAVAKOLI ,  Ramin GHAZNAVI YOUVALARI

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method is provided for computing predetermined loss terms based on original data and decoded data; training one or more neural networks of a system by using the predetermined loss terms; updating weights for one or more of other loss terms; and determining trade-offs between predetermined objectives of the system. Corresponding apparatuses and computer program products are also provided.

公开(公告)号：US20230164336A1

公开(公告)日：2023-05-25

申请号：US17917153

申请日：2021-03-30

Applicant: Nokia Technologies OY

Inventor： Francesco CRICRI ,  Nam LE ,  Hamed REZAZADEGAN TAVAKOLI ,  Honglei ZHANG ,  Miska Matias HANNUKSELA ,  Emre Baris AKSU

IPC: H04N19/42 ,  H04N19/192 ,  G06N3/0455 ,  G06N3/084

CPC classification number: H04N19/42 ,  H04N19/192 ,  G06N3/0455 ,  G06N3/084

Abstract: Example embodiments provide a system for training a data coding pipeline including a feature extractor neural network, an encoder neural network, and a decoder neural network configured to reconstruct input data based on encoded features. A plurality of losses corresponding to different tasks may be determined for the coding pipeline. Tasks may be performed based on an output of the coding pipeline. A weight update may be determined for at least a subset of the coding pipeline based on the plurality of losses. The weight update may be configured to reduce a number of iterations for fine-tuning the coding pipeline for one of the tasks. This enables faster adaptation of the coding pipeline for one of the tasks after deployment of the coding pipeline. Apparatuses, methods, and computer programs are disclosed. Apparatuses, methods, and computer programs are disclosed.