公开(公告)号：US20240202493A1

公开(公告)日：2024-06-20

申请号：US18510199

申请日：2023-11-15

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hyunwoo CHO ,  Iksoo SHIN ,  Chang Sik CHO

IPC: G06N3/04

CPC classification number: G06N3/04

Abstract: Provided is a method of searching for optimal neural network architecture based on channel concatenation. The method includes adjusting spatial size information of an input feature map candidate group so that the spatial size information of the input feature map candidate group corresponds to spatial size information of an output feature map, performing a channel-based concatenation operation on the input feature map candidate group, and additionally extending an output feature map that is the results of the channel-concatenated operation to the input feature map candidate group.

公开(公告)号：US20170255877A1

公开(公告)日：2017-09-07

申请号：US15167861

申请日：2016-05-27

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hyunwoo CHO ,  Do Hyung KIM ,  Cheol RYU ,  Seok Jin YOON ,  Jae Ho LEE ,  Hyung-Seok LEE ,  Kyung Hee LEE

IPC: G06N99/00

CPC classification number: G06N20/00 ,  G06F9/5083

Abstract: There is provided a heterogeneous computing method. A heterogeneous computing method includes performing offline learning on an algorithm using compilations and runtimes of application programs, executing a first application program in a mobile device, distributing a workload to a central processing unit (CPU) and a graphic processing unit (GPU) in the first application program, using the algorithm, performing online learning to reset the workload distributed to the CPU and GPU in the first application program, and resetting the workload distributed to the CPU and GPU in the first application program, corresponding to a result of the online learning.