Invention Grant
- Patent Title: Method of training neural network, and recognition method and apparatus using neural network
-
Application No.: US15691916Application Date: 2017-08-31
-
Publication No.: US10902292B2Publication Date: 2021-01-26
- Inventor: Hyoa Kang
- Applicant: SAMSUNG ELECTRONICS CO., LTD.
- Applicant Address: KR Suwon-si
- Assignee: SAMSUNG ELECTRONICS CO., LTD.
- Current Assignee: SAMSUNG ELECTRONICS CO., LTD.
- Current Assignee Address: KR Suwon-si
- Agency: NSIP Law
- Priority: KR10-2016-0171650 20161215
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06K9/66 ; G06N3/04 ; G06N3/08

Abstract:
A training method of a neural network, and a recognition method and apparatus using the neural network are disclosed. The recognition method using the neural network includes obtaining a feature vector generated from a hidden layer of the neural network, in response to data being entered to an input layer of the neural network, and determining a reliability of a recognition result for the data using the feature vector and clusters.
Public/Granted literature
- US20180174001A1 METHOD OF TRAINING NEURAL NETWORK, AND RECOGNITION METHOD AND APPARATUS USING NEURAL NETWORK Public/Granted day:2018-06-21
Information query