公开(公告)号：US20200311552A1

公开(公告)日：2020-10-01

申请号：US16829205

申请日：2020-03-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yong A ,  Gaofei Wang ,  Zhenbo Luo ,  Shuli Yang ,  Bin Sun ,  Pei Fu ,  Hua Wang

IPC: G06N3/08 ,  G06N3/04

Abstract: A method for compressing a machine learning model by an electronic device. The method may comprise determining a compression parameter of a set hidden layer in a model based on a pruning number of respective channels included in the set hidden layer and a pruning loss of each hidden layer of the model; and compressing the model based on the compression parameter of the set hidden layer. The compression parameter may be related to a pruning of the model.

公开(公告)号：US10437466B2

公开(公告)日：2019-10-08

申请号：US15551828

申请日：2016-02-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yingying Jiang ,  Shuli Yang ,  Youxin Chen ,  Bo Wang

IPC: G06F3/0488 ,  G06F17/24 ,  G06K9/72 ,  G06F17/10 ,  G06F17/12 ,  G06F17/16

Abstract: A formula inputting method is provided. The formula inputting method includes receiving a handwriting input of a user; obtaining handwriting content based on the handwriting input of the user; determining at least one or more recommended content based on the handwriting content; and displaying the handwriting content and the one or more recommended content.