Invention Grant
- Patent Title: Method and apparatus for training a neural network using modality signals of different domains
-
Application No.: US16131841Application Date: 2018-09-14
-
Publication No.: US11640518B2Publication Date: 2023-05-02
- Inventor: Sunghun Kang , Chang Dong Yoo
- Applicant: Samsung Electronics Co., Ltd. , Korea Advanced Institute Of Science And Technology
- Applicant Address: KR Suwon-si; KR Daejeon
- 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: Jefferson IP Law, LLP
- Priority: KR10-2017-0153971 20171117
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N3/08 ; G06N5/025

Abstract:
An apparatus and a method for the disclosure relates to an artificial intelligence (AI) system that simulates functions such as recognition and determination of the human brain by using a machine training algorithm such as deep learning and an application of the AI system are provided. A neural network training method includes obtaining target modality signals of a first domain aligned in a time order and auxiliary modality signals of a second domain that are not aligned in the time order, extracting characteristic information of the target modality signals using a first neural network model, estimating the time order of the auxiliary modality signals using a second neural network model, and training the first neural network model based on a result of the estimation and the characteristic information.
Public/Granted literature
- US20190156203A1 NEURAL NETWORK TRAINING METHOD AND DEVICE Public/Granted day:2019-05-23
Information query