公开(公告)号：US20170083772A1

公开(公告)日：2017-03-23

申请号：US15266231

申请日：2016-09-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Chang Hyun KIM ,  Tae Sup MOON ,  Dong Hwa LEE ,  Hyun Jin CHOI ,  Ki Hwan CHOI

IPC: G06K9/00 ,  G06N7/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62 ,  B60Q9/00

CPC classification number: G06K9/00791 ,  B60Q9/00 ,  G06K9/4642 ,  G06K9/6223 ,  G06K9/6226 ,  G06K9/72 ,  G06N3/0445 ,  G06N3/08 ,  G06N7/005

Abstract: Disclosed are methods and apparatuses for object recognition using an artificial neural network. An object recognition apparatus includes an adjacent pixel setter configured to set the neighboring pixel pairs in the image frame, each neighboring pixel pair including first pixel and one or more second pixels adjacent to the first pixel, a labeler configured to label the first pixel using deep neural network-based model based on probability density function value of the neighboring pixel pairs, and an object recognizer configured to recognize an object based on the labeled first pixel.

公开(公告)号：US20240386278A1

公开(公告)日：2024-11-21

申请号：US18663969

申请日：2024-05-14

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Seoul National University R&DB Foundation

Inventor： Hong Joon AHN ,  Jinu HYEON ,  Tae Sup MOON

IPC: G06N3/092 ,  G06N3/045

Abstract: A method and device for performing continual learning are provided. The method of performing continual learning of tasks in a set of tasks includes learning a first model based on training data corresponding to a current task in the set of tasks, learning a second model based on information on the current task and information on a previous learning task in the set of tasks, and resetting the first model.