公开(公告)号：US20200042896A1

公开(公告)日：2020-02-06

申请号：US16518104

申请日：2019-07-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： JEONG-HOON KO ,  Jae-Jun Lee ,  Seong-Je Kim ,  In Huh ,  Chang-Wook Jeong

IPC: G06N20/00 ,  G06F11/34 ,  G06F17/18 ,  G06F17/15

Abstract: A method of selecting a model of machine learning executed by a processor is provided. The method includes: receiving at least one data-set; configuring a configuration space for machine learning of the at least one data-set; extracting, from the at least one data-set, a meta-feature including quantitative information about the data-set; calculating performance of the machine learning for the at least one data-set based on a plurality of configurations included in the configuration space; executing meta-learning based on the meta-feature, the plurality of configurations, and the calculated performance; and optimizing the configuration space based on a result of executing the meta-learning.

公开(公告)号：US10217816B2

公开(公告)日：2019-02-26

申请号：US15296077

申请日：2016-10-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Krishna Kumar Bhuwalka ,  Seong-Je Kim ,  Jong-Chol Kim ,  Hyun-Woo Kim

IPC: B82Y10/00 ,  H01L29/06 ,  H01L29/10 ,  H01L29/66 ,  H01L27/088 ,  H01L29/423 ,  H01L29/775 ,  H01L21/8234

Abstract: A semiconductor device includes a plurality of channels, source/drain layers, and a gate structure. The channels are sequentially stacked on a substrate and are spaced apart from each other in a first direction perpendicular to a top surface of the substrate. The source/drain layers are connected to the channels and are at opposite sides of the channels in a second direction parallel to the top surface of the substrate. The gate structure encloses the channels. The channels have different lengths in the second direction and different thicknesses in the first direction.

公开(公告)号：US11681947B2

公开(公告)日：2023-06-20

申请号：US16518104

申请日：2019-07-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jeong-Hoon Ko ,  Jae-Jun Lee ,  Seong-Je Kim ,  In Huh ,  Chang-Wook Jeong

IPC: G06N20/00 ,  G06F17/15 ,  G06F17/18 ,  G06F11/34

CPC classification number: G06N20/00 ,  G06F11/3495 ,  G06F17/15 ,  G06F17/18

Abstract: A method of selecting a model of machine learning executed by a processor is provided. The method includes: receiving at least one data-set; configuring a configuration space for machine learning of the at least one data-set; extracting, from the at least one data-set, a meta-feature including quantitative information about the data-set; calculating performance of the machine learning for the at least one data-set based on a plurality of configurations included in the configuration space; executing meta-learning based on the meta-feature, the plurality of configurations, and the calculated performance; and optimizing the configuration space based on a result of executing the meta-learning.

公开(公告)号：US11515391B2

公开(公告)日：2022-11-29

申请号：US17070221

申请日：2020-10-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Krishna Kumar Bhuwalka ,  Seong-Je Kim ,  Jong-Chol Kim ,  Hyun-Woo Kim

IPC: H01L29/06 ,  H01L29/66 ,  H01L29/423 ,  B82Y10/00 ,  H01L29/775 ,  H01L29/10 ,  H01L29/786 ,  H01L21/8234

Abstract: A semiconductor device includes a plurality of channels, source/drain layers, and a gate structure. The channels are sequentially stacked on a substrate and are spaced apart from each other in a first direction perpendicular to a top surface of the substrate. The source/drain layers are connected to the channels and are at opposite sides of the channels in a second direction parallel to the top surface of the substrate. The gate structure encloses the channels. The channels have different lengths in the second direction and different thicknesses in the first direction.