公开(公告)号：US11797461B2

公开(公告)日：2023-10-24

申请号：US17858506

申请日：2022-07-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyunsun Park ,  Jun-Woo Jang ,  Yoojin Kim ,  Channoh Kim

IPC: G06F13/16 ,  G06N3/08

CPC classification number: G06F13/1668 ,  G06N3/08

Abstract: A data transmission method for a convolution operation, and a convolution operation apparatus including a fetcher that includes a loader, at least one sender, a buffer controller, and a reuse buffer. The method includes loading, by the loader, input data of an input feature map according to a loading order, based on input data stored in the reuse buffer, a shape of a kernel to be used for a convolution operation, and two-dimensional (2D) zero-value information of weights of the kernel; storing, by the buffer controller, the loaded input data in the reuse buffer of an address cyclically assigned according to the loading order; and selecting, by each of the at least one sender, input data corresponding to each output data of a convolution operation among the input data stored in the reuse buffer, based on one-dimensional (1D) zero-value information of the weights, and outputting the selected input data.

公开(公告)号：US11521039B2

公开(公告)日：2022-12-06

申请号：US16168418

申请日：2018-10-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyunsun Park ,  Wonjo Lee ,  Sehwan Lee ,  Seungwon Lee

IPC: G06N3/04 ,  G06N3/08 ,  G06F17/15 ,  G06N5/04 ,  G06F16/901

Abstract: A process-implemented neural network method includes obtaining a plurality of kernels and an input feature map; determining a pruning index indicating a weight location where pruning is to be performed commonly within the plurality of kernels; and performing a Winograd-based convolution operation by pruning a weight corresponding to the determined pruning index with respect to each of the plurality of kernels.

公开(公告)号：US12175376B2

公开(公告)日：2024-12-24

申请号：US18186163

申请日：2023-03-18

Applicant: Samsung Electronics Co., Ltd. ,  Seoul National University R&DB Foundation

Inventor： Hyunsun Park ,  Soonhoi Ha ,  Donghyun Kang ,  Jintaek Kang

IPC: G06N3/10 ,  G06N3/04 ,  G06N3/063

Abstract: A processor-implemented method of a neural network includes obtaining intermediate pooling results, respectively corresponding to sub-pooling kernels obtained by decomposing an original pooling kernel, by performing a pooling operation on input pixels included in a current window in an input feature map with the sub-pooling kernels, obtaining a final pooling result corresponding to the current window by post-processing the intermediate pooling results, and determining an output pixel value of an output feature map, based on the final pooling result, wherein the current window is determined according to the original pooling kernel having been slid, according to a raster scan order, in the input feature map.

公开(公告)号：US12026611B2

公开(公告)日：2024-07-02

申请号：US16426744

申请日：2019-05-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyunsun Park ,  Junhaeng Lee ,  Shinhaeng Kang

IPC: G06N3/08 ,  G06N5/04

CPC classification number: G06N3/08 ,  G06N5/04

Abstract: A method of quantizing parameters of a neural network includes calculating, for each of the parameters, a bit shift value indicating a degree outside a bit range of a fixed-point format for quantizing the parameters, updating the fixed-point format based on the calculated bit shift values of the parameters, and quantizing parameters updated in a learning or inference process according to the updated fixed-point format.

公开(公告)号：US11875255B2

公开(公告)日：2024-01-16

申请号：US16803342

申请日：2020-02-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyunsun Park ,  Yoojin Kim ,  Hyeongseok Yu ,  Sehwan Lee ,  Junwoo Jang

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: A method of processing data in a neural network, includes identifying a sparsity of input data, based on valid information included in the input data in which the input data includes valid values and invalid values, generate rearranged input data, based on a form of the sparsity by rearranging, in the input data, location of at least one of the valid values and the invalid values, and generating, by performing a convolution on the rearranged input data in the neural network, an output.

公开(公告)号：US11409675B2

公开(公告)日：2022-08-09

申请号：US17330229

申请日：2021-05-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyunsun Park ,  Jun-Woo Jang ,  Yoojin Kim ,  Channoh Kim

IPC: G06F13/16 ,  G06N3/08

Abstract: A data transmission method for a convolution operation, and a convolution operation apparatus including a fetcher that includes a loader, at least one sender, a buffer controller, and a reuse buffer. The method includes loading, by the loader, input data of an input feature map according to a loading order, based on input data stored in the reuse buffer, a shape of a kernel to be used for a convolution operation, and two-dimensional (2D) zero-value information of weights of the kernel; storing, by the buffer controller, the loaded input data in the reuse buffer of an address cyclically assigned according to the loading order; and selecting, by each of the at least one sender, input data corresponding to each output data of a convolution operation among the input data stored in the reuse buffer, based on one-dimensional (1D) zero-value information of the weights, and outputting the selected input data.

公开(公告)号：US11899744B2

公开(公告)日：2024-02-13

申请号：US16851361

申请日：2020-04-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Songyi Han ,  Hyunsun Park

IPC: G06F17/16 ,  G06N3/08 ,  G06F18/213

CPC classification number: G06F17/16 ,  G06F18/213 ,  G06N3/08

Abstract: A neural network apparatus for performing a matrix multiplication operation includes a memory having at least one program stored therein and a processor to perform one or more operations by executing the at least one program. The processor can determine whether to divide an initial weight in one of a column direction and a row direction according to whether a reshape operation and a transpose operation are performed before or after a matrix multiplication operation and generate division weights by dividing the initial weight by a head count in the determined direction. Also, the processor can generate intermediate feature maps by performing a matrix multiplication operation between the input feature map and the division weights and generate a final feature map based on the intermediate feature maps.

公开(公告)号：US11875251B2

公开(公告)日：2024-01-16

申请号：US16244644

申请日：2019-01-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junhaeng Lee ,  Hyunsun Park ,  Sehwan Lee ,  Seungwon Lee

IPC: G06N3/08 ,  G06N3/0495

CPC classification number: G06N3/08 ,  G06N3/0495

Abstract: A neural network method and apparatus is provided. A processor-implemented neural network method includes determining, based on a determined number of classes of input data, a precision for a neural network layer outputting an operation result, and processing parameters of the layer according to the determined precision.

公开(公告)号：US11640538B2

公开(公告)日：2023-05-02

申请号：US16826373

申请日：2020-03-23

Applicant: Samsung Electronics Co., Ltd. ,  Seoul National University R&DB Foundation

Inventor： Hyunsun Park ,  Soonhoi Ha ,  Donghyun Kang ,  Jintaek Kang

IPC: G06N3/10 ,  G06N3/063 ,  G06N3/04

Abstract: A processor-implemented method of a neural network includes obtaining intermediate pooling results, respectively corresponding to sub-pooling kernels obtained by decomposing an original pooling kernel, by performing a pooling operation on input pixels included in a current window in an input feature map with the sub-pooling kernels, obtaining a final pooling result corresponding to the current window by post-processing the intermediate pooling results, and determining an output pixel value of an output feature map, based on the final pooling result, wherein the current window is determined according to the original pooling kernel having been slid, according to a raster scan order, in the input feature map.

公开(公告)号：US11544549B2

公开(公告)日：2023-01-03

申请号：US16106703

申请日：2018-08-21

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Junhaeng Lee ,  Hyunsun Park ,  Yeongjae Choi

IPC: G06N3/08 ,  G06N3/063 ,  G06F7/483

Abstract: A processor-implemented neural network method includes calculating individual update values for a weight assigned to a connection relationship between nodes included in a neural network; generating an accumulated update value by accumulating the individual update values in an accumulation buffer; and training the neural network by updating the weight using the accumulated update value in response to the accumulated update value being equal to or greater than a threshold value.