公开(公告)号：US20230117033A1

公开(公告)日：2023-04-20

申请号：US18084948

申请日：2022-12-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junhaeng LEE ,  Seungwon LEE ,  Sangwon HA ,  Wonjo LEE

IPC: H03M7/24 ,  G06N3/063 ,  G06F7/483 ,  G06F7/499 ,  G06F7/544

Abstract: A method of generating a fixed-point quantized neural network includes analyzing a statistical distribution for each channel of floating-point parameter values of feature maps and a kernel for each channel from data of a pre-trained floating-point neural network, determining a fixed-point expression of each of the parameters for each channel statistically covering a distribution range of the floating-point parameter values based on the statistical distribution for each channel, determining fractional lengths of a bias and a weight for each channel among the parameters of the fixed-point expression for each channel based on a result of performing a convolution operation, and generating a fixed-point quantized neural network in which the bias and the weight for each channel have the determined fractional lengths.

公开(公告)号：US20240185029A1

公开(公告)日：2024-06-06

申请号：US18437370

申请日：2024-02-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjo LEE ,  Seungwon LEE ,  Junhaeng LEE

IPC: G06N3/045 ,  G06N3/047 ,  G06N3/084

CPC classification number: G06N3/045 ,  G06N3/047 ,  G06N3/084

Abstract: According to a method and apparatus for neural network quantization, a quantized neural network is generated by performing learning of a neural network, obtaining weight differences between an initial weight and an updated weight determined by the learning of each cycle for each of layers in the first neural network, analyzing a statistic of the weight differences for each of the layers, determining one or more layers, from among the layers, to be quantized with a lower-bit precision based on the analyzed statistic, and generating a second neural network by quantizing the determined one or more layers with the lower-bit precision.

公开(公告)号：US20210081798A1

公开(公告)日：2021-03-18

申请号：US16835532

申请日：2020-03-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minkyoung CHO ,  Wonjo LEE ,  Seungwon LEE

IPC: G06N3/08 ,  G06N3/04

Abstract: A method and apparatus for the pruning of a neural network is provided. The method sets a weight threshold value based on a weight distribution of layers included in a neural network, predicts a change of inference accuracy of a neural network by pruning of each layer based on the weight threshold value, determines a current subject layer to be pruned with a weight threshold value among the layers included in the neural network, and prunes a determined current subject layer.

公开(公告)号：US20240346317A1

公开(公告)日：2024-10-17

申请号：US18752163

申请日：2024-06-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minkyoung CHO ,  Wonjo LEE ,  Seungwon LEE

IPC: G06N3/082 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: A method and apparatus for the pruning of a neural network is provided. The method sets a weight threshold value based on a weight distribution of layers included in a neural network, predicts a change of inference accuracy of a neural network by pruning of each layer based on the weight threshold value, determines a current subject layer to be pruned with a weight threshold value among the layers included in the neural network, and prunes a determined current subject layer.

公开(公告)号：US20230206031A1

公开(公告)日：2023-06-29

申请号：US18116553

申请日：2023-03-02

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjo LEE ,  Seungwon LEE ,  Junhaeng LEE

IPC: G06N3/045 ,  G06N3/084 ,  G06N3/047

CPC classification number: G06N3/045 ,  G06N3/084 ,  G06N3/047

Abstract: According to a method and apparatus for neural network quantization, a quantized neural network is generated by performing learning of a neural network, obtaining weight differences between an initial weight and an updated weight determined by the learning of each cycle for each of layers in the first neural network, analyzing a statistic of the weight differences for each of the layers, determining one or more layers, from among the layers, to be quantized with a lower-bit precision based on the analyzed statistic, and generating a second neural network by quantizing the determined one or more layers with the lower-bit precision.

公开(公告)号：US20200218962A1

公开(公告)日：2020-07-09

申请号：US16738338

申请日：2020-01-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjo LEE ,  Seungwon LEE ,  Junhaeng LEE

IPC: G06N3/04 ,  G06N3/08

Abstract: According to a method and apparatus for neural network quantization, a quantized neural network is generated by performing learning of a neural network, obtaining weight differences between an initial weight and an updated weight determined by the learning of each cycle for each of layers in the first neural network, analyzing a statistic of the weight differences for each of the layers, determining one or more layers, from among the layers, to be quantized with a lower-bit precision based on the analyzed statistic, and generating a second neural network by quantizing the determined one or more layers with the lower-bit precision.

公开(公告)号：US20190130250A1

公开(公告)日：2019-05-02

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 ,  G06F17/30 ,  G06N5/04 ,  G06F17/15

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：US20190042948A1

公开(公告)日：2019-02-07

申请号：US16051788

申请日：2018-08-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junhaeng LEE ,  Seungwon LEE ,  Sangwon HA ,  Wonjo LEE

IPC: G06N3/10 ,  G06N3/04 ,  G06F7/544

Abstract: A method of generating a fixed-point quantized neural network includes analyzing a statistical distribution for each channel of floating-point parameter values of feature maps and a kernel for each channel from data of a pre-trained floating-point neural network, determining a fixed-point expression of each of the parameters for each channel statistically covering a distribution range of the floating-point parameter values based on the statistical distribution for each channel, determining fractional lengths of a bias and a weight for each channel among the parameters of the fixed-point expression for each channel based on a result of performing a convolution operation, and generating a fixed-point quantized neural network in which the bias and the weight for each channel have the determined fractional lengths.