-
公开(公告)号：US11934939B2
公开(公告)日：2024-03-19
申请号：US18116553
申请日：2023-03-02
Applicant: Samsung Electronics Co., Ltd.
Inventor： Wonjo Lee , Seungwon Lee , Junhaeng Lee
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：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：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
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.
-
公开(公告)号：US20160106327A1
公开(公告)日：2016-04-21
申请号：US14884019
申请日：2015-10-15
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Youngzoon Yoon , Hyunsurk Ryu , Kyoobin LEE , Jaesoong LEE , Junhaeng Lee , Seunghoon HAN
CPC classification number: A61B5/02108 , A61B5/0261 , A61B5/681 , A61B5/742
Abstract: An apparatus for acquiring bio-information includes a light source configured to radiate a laser beam to a region of interest including a blood vessel; a sensor configured to sense, from the region of interest, a change of a laser speckle generated by the radiated laser beam; and a controller configured to obtain a bio-signal indicating a change in a blood flow in the blood vessel based on the sensed change of the laser speckle.
Abstract translation: 一种用于获取生物信息的装置，包括配置成将激光束照射到包括血管的感兴趣区域的光源; 传感器，被配置为从感兴趣的区域感测由辐射激光束产生的激光散斑的变化; 以及控制器，被配置为基于感测到的激光散斑的变化来获得指示血管中血流变化的生物信号。
-
公开(公告)号：US11836603B2
公开(公告)日：2023-12-05
申请号：US16282748
申请日：2019-02-22
Applicant: Samsung Electronics Co., Ltd.
Inventor： SangWon Ha , Junhaeng Lee
Abstract: A neural network method of parameter quantization obtains channel profile information for first parameter values of a floating-point type in each channel included in each of feature maps based on an input in a first dataset to a floating-point parameters pre-trained neural network, and determines a probability density function (PDF) type, for each channel, appropriate for the channel profile information based on a classification network receiving the channel profile information as a dataset. The neural network method of parameter quantization determines a fixed-point representation, based on the determined PDF type, for each channel, statistically covering a distribution range of the first parameter values, and generates a fixed-point quantized neural network based on the fixed-point representation determined for each channel.
-
Patent Agency Ranking
公开(公告)号：US11625577B2
公开(公告)日：2023-04-11
申请号：US16738338
申请日：2020-01-09
Applicant: Samsung Electronics Co., Ltd.
Inventor： Wonjo Lee , Seungwon Lee , Junhaeng Lee
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：US11250320B2
公开(公告)日：2022-02-15
申请号：US15880690
申请日：2018-01-26
Inventor： Junhaeng Lee , Sungjoo Yoo , Eunhyeok Park
Abstract: Provided are a neural network method and an apparatus, the method including obtaining a set of floating point data processed in a layer included in a neural network, determining a weighted entropy based on data values included in the set of floating point data, adjusting quantization levels assigned to the data values based on the weighted entropy, and quantizing the data values included in the set of floating point data in accordance with the adjusted quantization levels.
-
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
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：US11588496B2
公开(公告)日：2023-02-21
申请号：US16051788
申请日：2018-08-01
Applicant: Samsung Electronics Co., Ltd.
Inventor： Junhaeng Lee , Seungwon Lee , Sangwon Ha , Wonjo Lee
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：US20220108178A1
公开(公告)日：2022-04-07
申请号：US17551572
申请日：2021-12-15
Inventor： Junhaeng Lee , Sungjoo Yoo , Eunhyeok Park
Abstract: Provided are a neural network method and an apparatus, the method including obtaining a set of floating point data processed in a layer included in a neural network, determining a weighted entropy based on data values included in the set of floating point data, adjusting quantization levels assigned to the data values based on the weighted entropy, and quantizing the data values included in the set of floating point data in accordance with the adjusted quantization levels.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.019 seconds)
