公开(公告)号：US12229660B2

公开(公告)日：2025-02-18

申请号：US17319679

申请日：2021-05-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngnam Hwang ,  Jaewon Yang

IPC: G06N3/065 ,  G06F7/544 ,  G06F17/16 ,  G06N3/049

Abstract: A compressed-truncated singular value decomposition (C-TSVD) based crossbar array apparatus is provided. The C-TSVD based crossbar array apparatus may include an original crossbar array in an m×n matrix having row input lines and column output lines and including cells of a resistance memory device, or two partial crossbar arrays obtained by decomposing the original crossbar array based on C-TSVD, an analog to digital converter (ADC) that converts output values of column output lines of sub-arrays obtained through array partitioning, an adder that sums up results of the ADC to correspond to the column output lines, and a controller that controls application of the original crossbar array or the two partial crossbar arrays. Input values are input to the row input lines, a weight is multiplied by the input values and accumulated results are output as output values of the column output lines.

公开(公告)号：US20230177815A1

公开(公告)日：2023-06-08

申请号：US17820911

申请日：2022-08-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sangchul Yeo ,  Jaewon Yang ,  Hyeok Lee ,  Sooryong Lee

IPC: G06V10/776 ,  G06T3/60 ,  G06V10/774

CPC classification number: G06V10/776 ,  G06T3/60 ,  G06V10/774

Abstract: A method of training a semiconductor process image generator includes training the semiconductor process image generator with a plurality of mask images including a first group and a second group, training the semiconductor process image generator with the second group and a first transformed group obtained by applying a transformation to the first group, and training the semiconductor process image generator with the first group and a second transformed group obtained by applying a transformation to the second group.

公开(公告)号：US10818347B2

公开(公告)日：2020-10-27

申请号：US16421855

申请日：2019-05-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ihor Vasyltsov ,  Youngnam Hwang ,  Jinmin Kim ,  Yongha Park ,  Hyunsik Park ,  Jaewon Yang

IPC: G11C11/54 ,  G11C11/408 ,  G11C11/4091 ,  G11C11/4096 ,  G06N3/04

Abstract: A semiconductor memory device includes a memory cell array including first memory cells and second memory cell, and a peripheral circuit. When a first command, a first address, and first input data are received, the peripheral circuit reads first data from the first memory cells based on the first address in response to the first command, performs a first operation by using the first data and the first input data, and reads second data from the second memory cells by using a result of the first operation.

公开(公告)号：US20250147096A1

公开(公告)日：2025-05-08

申请号：US18790237

申请日：2024-07-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaewon Yang ,  Younghoon Sohn ,  Souk Kim ,  Jaeho Kim ,  Jongbeom Kim ,  HyeonBo Shim ,  Minho Rim

IPC: G01R31/265

Abstract: A substrate inspection apparatus includes a laser light source configured to emit a laser beam, an optical splitter configured to split the laser beam into a first laser beam and a second laser beam, a delay stage configured to change a relative time delay of the second laser beam and optically connected to the optical splitter, a first modulator optically connected to the optical splitter and configured to change the first laser beam, and a feedback system configured to sense the second laser beam reflected from a substrate and configured to apply electrical feedback to the first modulator.

公开(公告)号：US20230418260A1

公开(公告)日：2023-12-28

申请号：US18106091

申请日：2023-02-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sangchul Yeo ,  Jaewon Yang ,  Hyeok Lee

IPC: G05B19/4099 ,  G05B13/02

CPC classification number: G05B19/4099 ,  G05B2219/45028 ,  G05B13/0265

Abstract: A reliable lithography model generating method reflecting a mask bias variation and a mask manufacturing method including the lithography model generating method are provided. The lithography model generating method includes preparing basic image data for learning, preparing transform image data that indicates a mask bias variation, generating a lithography model by performing deep learning by combining the basic image data and the transform image data, and verifying the lithography model.

公开(公告)号：US20220108159A1

公开(公告)日：2022-04-07

申请号：US17319679

申请日：2021-05-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngnam Hwang ,  Jaewon Yang

IPC: G06N3/063 ,  G06N3/04 ,  G06F17/16 ,  G06F7/544

Abstract: A compressed-truncated singular value decomposition (C-TSVD) based crossbar array apparatus is provided. The C-TSVD based crossbar array apparatus may include an original crossbar array in an m×n matrix having row input lines and column output lines and including cells of a resistance memory device, or two partial crossbar arrays obtained by decomposing the original crossbar array based on C-TSVD, an analog to digital converter (ADC) that converts output values of column output lines of sub-arrays obtained through array partitioning, an adder that sums up results of the ADC to correspond to the column output lines, and a controller that controls application of the original crossbar array or the two partial crossbar arrays. Input values are input to the row input lines, a weight is multiplied by the input values and accumulated results are output as output values of the column output lines.

公开(公告)号：US12299869B2

公开(公告)日：2025-05-13

申请号：US17849617

申请日：2022-06-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyeok Lee ,  Jaewon Yang ,  Sangchul Yeo ,  Eunju Kim ,  Sooryong Lee

IPC: G06T19/00 ,  A61B6/00 ,  A61B6/02 ,  G06F3/04815 ,  G06F3/04842 ,  G06F30/27 ,  G06T7/00 ,  G06V10/10 ,  G06V10/46

Abstract: An operating method of a computing device for predicting a profile using deep learning includes sampling a unique pattern in a full chip, extracting a contour of a resist profile of each of a plurality of heights by performing rigorous simulation corresponding to the unique pattern, preparing an input image and an output image corresponding to the contour of each of the plurality of heights, performing deep learning on the extracted contour using the input image and the output image, and generating a profile prediction model according to performing of the deep leaning.

公开(公告)号：US11294290B2

公开(公告)日：2022-04-05

申请号：US16911819

申请日：2020-06-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Woo-Yong Cho ,  Sangwook Kim ,  Jaewon Yang

IPC: G03F7/20 ,  H01L21/308 ,  H01L21/027

Abstract: Disclosed are reticle fabrication methods and semiconductor device fabrication methods. The reticle fabrication method includes performing a photolithography process on a test substrate using a first reticle having first patterns, measuring the test substrate to obtain measured images, designing a second reticle having second patterns, redesigning the second reticle based on a margin of the photolithography process, and manufacturing the redesigned second reticle. Redesigning the second reticle includes obtaining sample images from the measured images when the first patterns are the same as the second patterns, obtaining contour images that have contours of sample patterns in the sample images, overlapping the contours to obtain a contour overlay value, and comparing the contour overlay value with a reference value to determine defects of the second patterns.

公开(公告)号：US20230196545A1

公开(公告)日：2023-06-22

申请号：US17849617

申请日：2022-06-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyeok Lee ,  Jaewon Yang ,  Sangchul Yeo ,  Eunju Kim ,  Sooryong Lee

IPC: G06T7/00 ,  G06V10/46 ,  G06V10/10 ,  G06F30/27

CPC classification number: G06T7/0006 ,  G06V10/46 ,  G06V10/10 ,  G06F30/27 ,  G06T2207/20081 ,  G06T2207/30148

Abstract: An operating method of a computing device for predicting a profile using deep learning includes sampling a unique pattern in a full chip, extracting a contour of a resist profile of each of a plurality of heights by performing rigorous simulation corresponding to the unique pattern, preparing an input image and an output image corresponding to the contour of each of the plurality of heights, performing deep learning on the extracted contour using the input image and the output image, and generating a profile prediction model according to performing of the deep leaning.