公开(公告)号：US20210358910A1

公开(公告)日：2021-11-18

申请号：US17384920

申请日：2021-07-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Dongsoo LEE ,  Wonkeun CHUNG ,  Hoonjoo NA ,  Suyoung BAE ,  Jaeyeol SONG ,  Jonghan LEE ,  HyungSuk JUNG ,  Sangjin HYUN

IPC: H01L27/092 ,  H01L29/786 ,  H01L21/8238 ,  H01L29/49 ,  H01L29/51 ,  H01L29/423

Abstract: Disclosed are semiconductor devices and methods of manufacturing the same. The semiconductor device comprises a first transistor on a substrate, and a second transistor on the substrate. Each of the first and second transistors includes a plurality of semiconductor patterns vertically stacked on the substrate and vertically spaced apart from each other, and a gate dielectric pattern and a work function pattern filling a space between the semiconductor patterns. The work function pattern of the first transistor includes a first work function metal layer, the work function pattern of the second transistor includes the first work function metal layer and a second work function metal layer, the first work function metal layer of each of the first and second transistors has a work function greater than that of the second work function metal layer, and the first transistor has a threshold voltage less than that of the second transistor.

公开(公告)号：US20210057030A1

公开(公告)日：2021-02-25

申请号：US16987618

申请日：2020-08-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Dongsoo LEE ,  Daehyun KIM ,  Guyeon WEI

IPC: G11C16/08 ,  G11C16/24 ,  G11C16/26 ,  G11C16/30 ,  G11C16/04 ,  G11C7/10

Abstract: A semiconductor device is provided. The device includes a memory that stores data in a non-volatile and volatile manner and a memory controller configured to control the memory. The memory includes a word line pair including a first and second word line, a first bit line pair orthogonal to the first and the second word line and including a first bit line and a first complementary bit line, and a memory cell pair including first and second memory cells adjacent to the first memory cell in a word line direction. A left node of the first memory cell, and a right node of the first memory cell and a left node of the second memory cell, are all connected to the first word line, and a value of the data stored in the memory cell pair in the non-volatile manner is determined according to the selected first word line.

公开(公告)号：US20200234131A1

公开(公告)日：2020-07-23

申请号：US16727323

申请日：2019-12-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dongsoo LEE ,  Sejung KWON ,  Parichay KAPOOR ,  Byeoungwook KIM

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/16

Abstract: An electronic apparatus is provided. The electronic apparatus includes sample data and memory storing a first matrix included in an artificial intelligence model trained based on sample data, and a processor configured to prunes each of a plurality of first elements included in the first matrix based on a first threshold, and acquire a first pruning index matrix that indicates whether each of the plurality of first elements has been pruned with binary data, factorize the first matrix to a second matrix of which size was determined based on the number of rows and the rank, and a third matrix of which size was determined based on the rank and the number of columns of the first matrix, prunes each of a plurality of second elements included in the second matrix based on a second threshold, and acquire a second pruning index matrix that indicates whether each of the plurality of second elements has been pruned with binary data, prunes each of a plurality of third elements included in the third matrix based on a third threshold, and acquire a third pruning index matrix that indicates whether each of the plurality of third elements has been pruned with binary data, acquire a final index matrix based on the second pruning index matrix and the third pruning index matrix, and update at least one of the second pruning index matrix or the third pruning index matrix by comparing the final index matrix with the first pruning index matrix.

公开(公告)号：US20230244441A1

公开(公告)日：2023-08-03

申请号：US18131164

申请日：2023-04-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Byeoungwook KIM ,  Dongsoo LEE ,  Sejung KWON ,  Yeonju RO ,  Baeseong PARK ,  Yongkweon JEON

IPC: G06F5/01 ,  G06F7/487 ,  G06F7/485 ,  G06F7/544

CPC classification number: G06F5/01 ,  G06F7/4876 ,  G06F7/485 ,  G06F7/5443

Abstract: An electronic device and a control method therefor are disclosed. An electronic device of the present disclosure includes a processor, which quantizes weight data with a combination of sign data and scaling factor data to obtain quantized data, and may input the first input data into a first module to obtain second input data in which exponents of input values included in the first input data are converted to the same value; input the second input data and the sign data into a second module to determine the signs of input values and perform calculations between the input values of which signs are determined to obtain first output data; input the first output data into a third module to normalize output values included in the first output data; and perform a multiplication operation on data including the normalized output values and the scaling factor data to obtain second output data.

公开(公告)号：US20220138628A1

公开(公告)日：2022-05-05

申请号：US17508593

申请日：2021-10-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dongsoo LEE

IPC: G06N20/00

Abstract: Provided is a method, performed by an electronic device, of updating a pre-trained artificial intelligence (AI) model may include obtaining a sum, of at least two first factor values to which at least two second factor values are respectively applied, as a quantized value of a first weight value from among a plurality of weight values included in the pre-trained AI model; obtaining training data for updating the pre-trained AI model; updating the pre-trained AI model based on the the training data.

公开(公告)号：US20200074283A1

公开(公告)日：2020-03-05

申请号：US16555331

申请日：2019-08-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Parichay KAPOOR ,  Saehyung LEE ,  Dongsoo LEE ,  Byeoungwook KIM

IPC: G06N3/06 ,  G06N3/08

Abstract: An electronic apparatus is provided. The electronic apparatus includes a storage storing a matrix included in an artificial intelligence model, and a processor. The processor divides data included in at least a portion of the matrix by one of rows and columns of the matrix to form groups, clusters the groups into clusters based on data included in each of the groups, and quantizes data divided by the other one of rows and columns of the matrix among data included in each of the clusters.

公开(公告)号：US20210351165A1

公开(公告)日：2021-11-11

申请号：US17077302

申请日：2020-10-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dongsoo LEE ,  Seogho LIM ,  Changho SHIN ,  Jongpil WON ,  Sangsu LEE

IPC: H01L25/075 ,  H01L33/60 ,  G02F1/13357 ,  H05K1/02

Abstract: A light emitting device includes a printed circuit board (PCB) substrate, a first ink layer covering the PCB substrate, the first ink layer having a first refractive index, light emitters on the first ink layer, and a second ink layer on the first ink layer and spaced apart from the light emitters, the second ink layer having a second refractive index different from the first refractive index.

公开(公告)号：US20210279589A1

公开(公告)日：2021-09-09

申请号：US17258617

申请日：2019-05-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dongsoo LEE ,  Parichay KAPOOR ,  Byeoungwook KIM

IPC: G06N3/08 ,  G06K9/62

Abstract: Disclosed is an electronic device. The electronic device comprises a storage in which sample data and a matrix included in an artificial intelligence model which is trained on the basis of the sample data are stored, and a processor, wherein the processor is configured to: on the basis of the sizes of a plurality of elements included in the matrix, obtain a first matrix pruned by converting values of elements in the number corresponding to a first proportion to zero values; on the basis of test data, obtain first accuracy of an artificial intelligence model including the first matrix; if the first accuracy is within a preset range with respect to a preset value, retrain the artificial intelligence model including the first matrix on the basis of the sample data; and, on the basis of the sizes of a plurality of elements included in the retrained first matrix, obtain a second matrix pruned by converting values of elements in the number corresponding to a second proportion, which is greater than the first proportion, to zero values.

公开(公告)号：US20210271981A1

公开(公告)日：2021-09-02

申请号：US17171582

申请日：2021-02-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Dongsoo LEE ,  Baeseong PARK ,  Byeoungwook KIM ,  Sejung KWON ,  Yongkweon JEON

IPC: G06N3/10 ,  G06F17/16 ,  G06N3/08

Abstract: An electronic apparatus performing an operation of a neural network model is provided. The electronic apparatus includes a memory configured to store weight data including quantized weight values of the neural network model; and a processor configured to obtain operation data based on input data and binary data having at least one bit value different from each other, generate a lookup table by matching the operation data with the binary data, identify operation data corresponding to the weight data from the lookup table, and perform an operation of the neural network model based on the identified operation data.

公开(公告)号：US20210111741A1

公开(公告)日：2021-04-15

申请号：US17130538

申请日：2020-12-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Dongsoo LEE ,  Sejung KWON ,  Byeoungwook KIM ,  Parichay KAPOOR ,  Baeseong PARK

IPC: H03M13/00 ,  G06N3/06 ,  H03M13/11 ,  H03M13/27

Abstract: A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.