Invention Grant
- Patent Title: Method of performing learning of deep neural network and apparatus thereof
-
Application No.: US16281737Application Date: 2019-02-21
-
Publication No.: US11809954B2Publication Date: 2023-11-07
- Inventor: Sungho Kang , Hyungdal Kwon , Cheon Lee , Yunjae Lim
- 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: Sughrue Mion, PLLC
- Priority: KR 20180020005 2018.02.20
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04 ; G06F7/58 ; G06N3/082

Abstract:
An encoding apparatus connected to a learning circuit processing learning of a deep neural network and configured to perform encoding for reconfiguring connection or disconnection of a plurality of edges in a layer of the deep neural network using an edge sequence generated based on a random number sequence and dropout information indicating a ratio between connected edges and disconnected edges of a plurality of edges included in a layer of the deep neural network.
Public/Granted literature
- US12001954B2 Method of performing learning of deep neural network and apparatus thereof Public/Granted day:2024-06-04
Information query