公开(公告)号：US12014268B2

公开(公告)日：2024-06-18

申请号：US16814578

申请日：2020-03-10

Applicant: LG ELECTRONICS INC.

Inventor： Seung-Kyun Oh ,  Jinseok Im ,  Sanghoon Kim

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: Disclosed is a batch normalization layer training method, which may be used in a neural network learning apparatus having limited operational processing capability and storage space. A batch normalization layer training method according to an embodiment of the present disclosure may perform batch normalization transform by setting the gradients of the standard deviation and the mean of the loss function to zero, and applying a normalized statistic value obtained from an initial neural network or a previous neural network to the gradient of the loss function. The neural network learning apparatus of the present disclosure may be connected or converged with an Artificial Intelligence module, an Unmanned Aerial Vehicle (UAV), a robot, an Augmented Reality (AR) apparatus, a Virtual Reality (VR), a 5G network service-related apparatus, etc.

公开(公告)号：US11436848B2

公开(公告)日：2022-09-06

申请号：US16865986

申请日：2020-05-04

Applicant: LG ELECTRONICS INC.

Inventor： Seongmock Yoo ,  Seung-Kyun Oh ,  Jinseok Im ,  Sanghoon Kim

IPC: G06V20/64 ,  G06K9/62 ,  G06N3/08 ,  G06V20/20

Abstract: An automatic labeling apparatus for object recognition and a method therefor are provided. The automatic labeling apparatus for object recognition is configured to apply an object recognition algorithm to each of a plurality of image frames so as to recognize an object, and in response to a determination that an object recognition result in at least one first image frame among the image frames corresponds to a predetermined error condition, automatically generate a data set on an object which is a target of object recognition by using an object recognition result of a second image frame other than the first image frame among the image frames and an object image of the first image frame. The object recognition algorithm, which is a neural network model generated through machine learning, may be stored in a memory or provided through a server in an artificial intelligence environment through a 5G network.