Invention Grant
- Patent Title: Neural network training method and device
-
Application No.: US16759878Application Date: 2017-11-16
-
Publication No.: US11681912B2Publication Date: 2023-06-20
- Inventor: Kyung-su Kim , Yukyung Choi , Sung-jin Kim
- Applicant: SAMSUNG ELECTRONICS CO., LTD. , KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
- Applicant Address: KR Suwon-si
- Assignee: SAMSUNG ELECTRONICS CO., LTD.,KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
- Current Assignee: SAMSUNG ELECTRONICS CO., LTD.,KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
- Current Assignee Address: KR Suwon-si; KR Daejeon
- Agency: Nixon & Vanderhye, P.c.
- International Application: PCT/KR2017/013043 2017.11.16
- International Announcement: WO2019/098418A 2019.05.23
- Date entered country: 2020-04-28
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04 ; G06T7/00 ; G06T7/55 ; G06T1/00 ; G06V20/00

Abstract:
Provided are an AI system for simulating functions such as recognition, determination, and so forth of human brains by using a mechanical learning algorithm like deep learning, or the like, and an application thereof. In particular, according to the AI system and the application thereof, a neural network training method includes obtaining a plurality of first images belonging to a particular category and a plurality of second images for which a category is not specified, training a neural network model for category recognition, based on the plurality of first images belonging to the particular category, recognizing at least one second image corresponding to the particular category among the plurality of second images, by using the trained neural network model, and modifying and refining the trained neural network model based on the recognized at least one second image.
Public/Granted literature
- US20210182664A1 NEURAL NETWORK TRAINING METHOD AND DEVICE Public/Granted day:2021-06-17
Information query