公开(公告)号：US20220374680A1

公开(公告)日：2022-11-24

申请号：US17529439

申请日：2021-11-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Young Jae KIM ,  Kae Weon YOU ,  Ji Ung LEE ,  Jun Haeng LEE ,  Kyoung Hoon KANG ,  Young Hak LEE

IPC: G06N3/04

Abstract: A deep learning device and system including the same is provided. The deep learning device comprising processing circuitry configured to determine whether a received image is abnormal using an anomaly detection model; merge at least some vectors extracted from the anomaly detection model; input, to a probability approximation model, principal components generated by a principal component analysis (PCA) to detect whether out of distribution (OOD) occurs in data of the received image; store a result of the determinations; and extract at least some the data in which the OOD occurs, as target labeling, using a target labeling extraction model when a rate of the data in which the OOD occurs is greater than or equal to a threshold value, wherein the anomaly detection model determines whether the received image is abnormal using the target labeling.

公开(公告)号：US20230393893A1

公开(公告)日：2023-12-07

申请号：US18099592

申请日：2023-01-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Byeong Cheon KIM ,  Young Jae KIM ,  Kyoung Hoon KANG ,  Young Hak LEE

IPC: G06F9/48 ,  G06F16/901

CPC classification number: G06F9/4881 ,  G06F16/901

Abstract: Provided is a system for distributed processing of data that includes a data storage storing raw data generated in a fabrication process in real time; a database storing information associated with each of the raw data in real time; a master service that monitors the database on the basis of the information, selects processing targets to be processed among the raw data, and stores metadata associated with the processing targets in a queue; and a plurality of pods which make requests for jobs to the master service, receive metadata from the master service, access the raw data stored in the data storage using the received metadata, and perform the jobs on the raw data.