公开(公告)号：US11423312B2

公开(公告)日：2022-08-23

申请号：US16141035

申请日：2018-09-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N3/08 ,  G06F17/15 ,  G06F7/02 ,  G06N3/04

Abstract: A method and system for constructing a convolutional neural network (CNN) model are herein disclosed. The method includes regularizing spatial domain weights, providing quantization of the spatial domain weights, pruning small or zero weights in a spatial domain, fine-tuning a quantization codebook, compressing a quantization output from the quantization codebook, and decompressing the spatial domain weights and using either sparse spatial domain convolution and sparse Winograd convolution after pruning Winograd-domain weights.

公开(公告)号：US10959236B2

公开(公告)日：2021-03-23

申请号：US16030779

申请日：2018-07-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Dongwoon Bai ,  Jungwon Lee ,  Sungyoon Cho ,  Heunchul Lee ,  Sungsoo Kim

IPC: H04W4/00 ,  H04W72/06 ,  H04L27/26 ,  H04J11/00 ,  H04L5/00

Abstract: A system and method for characterizing an interference demodulation reference signal (DMRS) in a piece of user equipment (UE), e.g., a mobile device. The UE determines whether the serving signal is transmitted in a DMRS-based transmission mode; if it is, the UE cancels the serving DMRS from the received signal; otherwise the UE cancels the serving data signal from the received signal. The remaining signal is then analyzed for the amount of power it has in each of four interference DMRS candidates, and hypothesis testing is performed to determine whether interference DMRS is present in the signal, and, if so, to determine the rank of the interference DMRS, and the port and scrambling identity of each of the interference DMRS layers.

公开(公告)号：US20180323929A1

公开(公告)日：2018-11-08

申请号：US16030779

申请日：2018-07-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Dongwoon Bai ,  Jungwon Lee ,  Sungyoon Cho ,  Heunchul Lee ,  Sungsoo Kim

IPC: H04L5/00 ,  H04B17/345 ,  H04W52/24 ,  H04W72/06

CPC classification number: H04L5/0048 ,  H04B17/345 ,  H04W52/243 ,  H04W72/06

Abstract: A system and method for characterizing an interference demodulation reference signal (DMRS) in a piece of user equipment (UE), e.g., a mobile device. The UE determines whether the serving signal is transmitted in a DMRS-based transmission mode; if it is, the UE cancels the serving DMRS from the received signal; otherwise the UE cancels the serving data signal from the received signal. The remaining signal is then analyzed for the amount of power it has in each of four interference DMRS candidates, and hypothesis testing is performed to determine whether interference DMRS is present in the signal, and, if so, to determine the rank of the interference DMRS, and the port and scrambling identity of each of the interference DMRS layers.

公开(公告)号：US20180205470A1

公开(公告)日：2018-07-19

申请号：US15462639

申请日：2017-03-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Dongwoon Bai ,  Linbo Li ,  Farrokh Etezadi ,  Jungwon Lee

IPC: H04B17/336 ,  H04L27/148 ,  H04L27/10

CPC classification number: H04B17/336 ,  H04B17/21 ,  H04L27/10 ,  H04L27/148

Abstract: A system and method for removing bias from a frequency estimate. A simulation is used to predict, for various values of the signal to noise ratio, a bias in a raw frequency estimate produced by a frequency estimation algorithm. A straight line is fit to simulated frequency offset estimates as a function of true frequency offset, and the reciprocal of the slope of the line is stored, as a multiplicative bias removal term, in a lookup table, for the simulated signal to noise ratio. In operation, the raw frequency estimate is multiplied by a multiplicative bias removal term, obtained from the lookup table, to form a corrected frequency offset estimate.

公开(公告)号：USD736804S1

公开(公告)日：2015-08-18

申请号：US29445971

申请日：2013-02-19

Applicant: Samsung Electronics Co., Ltd.

Designer： Yoo Jin Choi ,  Jang Won Seo ,  Yong Hwan Kwon ,  Woo Seok Hwang ,  Hee Jeong Bae ,  Myung Kwan Choi

公开(公告)号：US11451242B2

公开(公告)日：2022-09-20

申请号：US17009213

申请日：2020-09-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: H03M7/00 ,  H03M7/30 ,  H04N19/13 ,  H04N19/147 ,  G06N3/08 ,  H04L1/00 ,  G06N3/04 ,  H04N19/19

Abstract: A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method includes training a conditional autoencoder using a Lagrange multiplier and training a neural network that includes the conditional autoencoder with mixed quantization bin sizes.

公开(公告)号：US11321609B2

公开(公告)日：2022-05-03

申请号：US15433531

申请日：2017-02-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N3/08 ,  G06N3/063 ,  G06F17/16

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for performing network parameter quantization in deep neural networks are described. In one aspect, diagonals of a second-order partial derivative matrix (a Hessian matrix) of a loss function of network parameters of a neural network are determined and then used to weight (Hessian-weighting) the network parameters as part of quantizing the network parameters. In another aspect, the neural network is trained using first and second moment estimates of gradients of the network parameters and then the second moment estimates are used to weight the network parameters as part of quantizing the network parameters. In yet another aspect, network parameter quantization is performed by using an entropy-constrained scalar quantization (ECSQ) iterative algorithm. In yet another aspect, network parameter quantization is performed by quantizing the network parameters of all layers of a deep neural network together at once.

公开(公告)号：USD911368S1

公开(公告)日：2021-02-23

申请号：US29688267

申请日：2019-04-19

Applicant: Samsung Electronics Co., Ltd.

Designer： Carole Baijings ,  Jody Kocken ,  Stefan Scholten ,  Jae Julien ,  Yoo Jin Choi ,  Ji Hyae Kim ,  Hye Ryung Kim ,  Ji Hyun Lee ,  Hye Won Lee

公开(公告)号：USD910682S1

公开(公告)日：2021-02-16

申请号：US29688255

申请日：2019-04-19

Applicant: Samsung Electronics Co., Ltd.

Designer： Carole Baijings ,  Jody Kocken ,  Stefan Scholten ,  Jae Julien ,  Yoo Jin Choi ,  Ji Hyae Kim ,  Hye Ryung Kim ,  Ji Hyun Lee ,  Hye Won Lee

公开(公告)号：US10886943B2

公开(公告)日：2021-01-05

申请号：US16576166

申请日：2019-09-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: H03M7/30 ,  H04N19/147 ,  G06N3/08 ,  G06N3/04 ,  H04N19/19 ,  H04N19/13 ,  H04L1/00

Abstract: A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method includes training a conditional autoencoder using a Lagrange multiplier and training a neural network that includes the conditional autoencoder with mixed quantization bin sizes.