公开(公告)号：US12061955B2

公开(公告)日：2024-08-13

申请号：US16898890

申请日：2020-06-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： James Russell Geraci ,  Bichen Shi ,  Aonghus Lawlor ,  Barry Smyth ,  Neil Hurley ,  Ruihai Dong

IPC: G06N20/00 ,  G06F17/18 ,  G06N5/04

CPC classification number: G06N20/00 ,  G06F17/18 ,  G06N5/04

Abstract: Provided are an artificial intelligence (AI) system simulating a function of a human brain, such as cognition and judgment, using a machine learning algorithm, such as deep learning, and an application thereof. Also, provided is a method, performed by an electronic apparatus, of refining an artificial intelligence (AI) model, the method including: detecting information about a context of an electronic apparatus used to refine a local model stored in the electronic apparatus being changed; determining a gradient for refining the local model based on the changed information about the context; refining the local model based on the determined gradient; transmitting the gradient to a server; receiving, from the server, information about a global model refined based on the gradient; and refining the local model based on the received information.

公开(公告)号：US11531912B2

公开(公告)日：2022-12-20

申请号：US16846825

申请日：2020-04-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： James Russell Geraci ,  Bichen Shi ,  Aonghus Lawlor ,  Barry Smyth ,  Neil Hurley ,  Ruihai Dong

IPC: G06N20/00 ,  G06N5/04

Abstract: Provided are an artificial intelligence (AI) system simulating a function of a human brain, such as cognition and judgment, using a machine learning algorithm, such as deep learning, and an application thereof. Also, provided is a method, performed by an electronic apparatus, of refining an artificial intelligence (AI) model, the method including: detecting information about a context of an electronic apparatus used to refine a local model stored in the electronic apparatus being changed; determining a gradient for refining the local model based on the changed information about the context; refining the local model based on the determined gradient; transmitting the gradient to a server; receiving, from the server, information about a global model refined based on the gradient; and refining the local model based on the received information.