公开(公告)号：US20180293707A1

公开(公告)日：2018-10-11

申请号：US15671036

申请日：2017-08-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Jungwon Lee ,  Haoyu Ren

IPC: G06T3/40

Abstract: In a method for super resolution imaging, the method includes: receiving, by a processor, a low resolution image; generating, by the processor, an intermediate high resolution image having an improved resolution compared to the low resolution image; generating, by the processor, a final high resolution image based on the intermediate high resolution image and the low resolution image; and transmitting, by the processor, the final high resolution image to a display device for display thereby.

公开(公告)号：US09479291B2

公开(公告)日：2016-10-25

申请号：US14837763

申请日：2015-08-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hessam Mahdavifar ,  Mostafa El-Khamy ,  Jungwon Lee ,  Inyup Kang

IPC: H01L27/00 ,  H04L1/00 ,  H04L1/20

CPC classification number: H04L1/009 ,  H03M13/033 ,  H03M13/13 ,  H04L1/0009 ,  H04L1/0041 ,  H04L1/0057

Abstract: An apparatus and method of constructing a universal polar code is provided. The apparatus includes a first function block configured to polarize and degrade a class of channels Wj to determine a probability of error Pe,j of each bit-channel of Wj, wherein jε{1, 2, . . . , s}, in accordance with a bit-channel index i; a second function block configured to determine a probability of error Pe(i) for the universal polar code for each bit-channel index i; a third function block configured to sort the Pe(i); and a fourth function block configured to determine a largest number k of bit-channels such that a sum of corresponding k bit-channel error probabilities Pe(i) is less than or equal to a target frame error rate Pt for the universal polar code, wherein the indices corresponding to the k smallest Pe(i) are good bit-channels for the universal polar code.

Abstract translation: 提供了构成通用极性码的装置和方法。 该装置包括：第一功能块，被配置为使一类信道Wj偏振和降级，以确定Wj的每个位信道的误差概率Pe，j，其中j∈{1,2，...， 。 。 ，s}，根据位信道索引i; 第二功能块，被配置为确定每个位通道索引i的通用极性代码的误差Pe（i）的概率; 配置为对Pe（i）进行排序的第三功能块; 以及第四功能块，被配置为确定比特信道的最大数量k，使得相应的k个比特信道误差概率Pe（i）的和小于或等于所述通用极性码的目标帧错误率Pt， 其中对应于k个最小Pe（i）的索引是用于通用极性码的良好比特信道。

公开(公告)号：US09362956B2

公开(公告)日：2016-06-07

申请号：US14158571

申请日：2014-01-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hessam Mahdavifar ,  Mostafa El-Khamy ,  Jungwon Lee ,  Inyup Kang

IPC: H03M13/00 ,  H03M13/29 ,  H03M13/27 ,  H03M13/13 ,  H03M13/11 ,  H03M13/15

CPC classification number: H03M13/296 ,  H03M13/1102 ,  H03M13/13 ,  H03M13/1515 ,  H03M13/27 ,  H03M13/2707 ,  H04L1/0041 ,  H04L1/0065

Abstract: A concatenated encoder is provided that includes an outer encoder, a symbol interleaver and a polar inner encoder. The outer encoder is configured to encode a data stream using an outer code to generate outer codewords. The symbol interleaver is configured to interleave symbols of the outer codewords and generate a binary stream. The polar inner encoder is configured to encode the binary stream using a polar inner code to generate an encoded stream. A concatenated decoder is provided that includes a polar inner decoder, a symbol de-interleaver and an outer decoder. The polar inner decoder is configured to decode an encoded stream using a polar inner code to generate a binary stream. The symbol de-interleaver is configured to de-interleave symbols in the binary stream to generate outer codewords. The outer decoder is configured to decode the outer codewords using an outer code to generate a decoded stream.

Abstract translation: 提供了包括外部编码器，符号交织器和极内部编码器的级联编码器。 外编码器被配置为使用外码对数据流进行编码以产生外码字。 符号交织器被配置为交织外部码字的符号并生成二进制流。 极性内部编码器被配置为使用极性内部码来对二进制流进行编码以生成编码的流。 提供了包括极性内部解码器，符号解交织器和外部解码器的级联解码器。 极性内部解码器被配置为使用极性内部码来解码编码的流以生成二进制流。 符号解交织器被配置为对二进制流中的符号进行解交织以产生外部码字。 外部解码器被配置为使用外部码来解码外部码字以产生解码的流。

公开(公告)号：US12154030B2

公开(公告)日：2024-11-26

申请号：US17096734

申请日：2020-11-12

Applicant: Samsung Electronics Co., Ltd.

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

IPC: G06N3/08 ,  G06F17/18 ,  G06F18/2113 ,  G06F18/214 ,  G06F18/22 ,  G06N3/045 ,  G06N7/01

Abstract: A method for training a generator, by a generator training system including a processor and memory, includes: extracting training statistical characteristics from a batch normalization layer of a pre-trained model, the training statistical characteristics including a training mean μ and a training variance σ2; initializing a generator configured with generator parameters; generating a batch of synthetic data using the generator; supplying the batch of synthetic data to the pre-trained model; measuring statistical characteristics of activations at the batch normalization layer and at the output of the pre-trained model in response to the batch of synthetic data, the statistical characteristics including a measured mean {circumflex over (μ)}ψ and a measured variance {circumflex over (σ)}ψ2; computing a training loss in accordance with a loss function Lψ based on μ, σ2, {circumflex over (μ)}ψ, and {circumflex over (σ)}ψ2; and iteratively updating the generator parameters in accordance with the training loss until a training completion condition is met to compute the generator.

公开(公告)号：US20240362494A1

公开(公告)日：2024-10-31

申请号：US18524467

申请日：2023-11-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy

IPC: G06N3/098

CPC classification number: G06N3/098

Abstract: A system and a method are disclosed, the method including receiving, by a first local controller of a first edge device, an input associated with an environment in which the first edge device operates, using a first machine-learning algorithm, determining, by the first local controller, a parameter for a pre-trained modem algorithm of the first edge device based on the input, executing a task on the first edge device based on executing the pre-trained modem algorithm with the parameter, determining a result of executing the task, training the first machine-learning algorithm, generating a first update to the first machine-learning algorithm based on the training, sending the first update to a server, receiving, from the server, a server update to the first machine-learning algorithm, and based on the server update, updating the first machine-learning algorithm.

公开(公告)号：US20240355320A1

公开(公告)日：2024-10-24

申请号：US18371289

申请日：2023-09-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Behnam Babagholami Mohamadabadi ,  Mostafa El-Khamy ,  Kee-Bong Song

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/20

CPC classification number: G10L15/063 ,  G10L15/16 ,  G10L15/20

Abstract: A system including: one or more processors; and memory including instructions that, when executed by the one or more processors, cause the one or more processors to: generate augmented input data by mixing noise components of training data; train a first neural network based on the augmented input data and ground truth data of the training data to output a first prediction of clean speech; lock trainable parameters of the first neural network as a result of the training of the first neural network; and train a second neural network according to the augmented input data and predictions of the first neural network to output a second prediction of the clean speech.

公开(公告)号：US12033652B2

公开(公告)日：2024-07-09

申请号：US17827424

申请日：2022-05-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Amin Fazeli ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G10L21/0232 ,  G06N3/08 ,  G06N20/10 ,  G10L21/0208 ,  H04R3/04

CPC classification number: G10L21/0232 ,  G06N3/08 ,  G06N20/10 ,  H04R3/04 ,  G10L2021/02082

Abstract: A system for performing echo cancellation includes: a processor configured to: receive a far-end signal; record a microphone signal including: a near-end signal; and an echo signal corresponding to the far-end signal; extract far-end features from the far-end signal; extract microphone features from the microphone signal; compute estimated near-end features by supplying the microphone features and the far-end features to an acoustic echo cancellation module including a recurrent neural network including: an encoder including a plurality of gated recurrent units; and a decoder including a plurality of gated recurrent units; compute an estimated near-end signal from the estimated near-end features; and transmit the estimated near-end signal to the far-end device. The recurrent neural network may include a contextual attention module; and the recurrent neural network may take, as input, a plurality of error features computed based on the far-end features, the microphone features, and acoustic path parameters.

公开(公告)号：US11979175B2

公开(公告)日：2024-05-07

申请号：US17941318

申请日：2022-09-09

Applicant: Samsung Electronics Co., Ltd.

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

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

CPC classification number: H03M7/6011 ,  G06N3/04 ,  G06N3/08 ,  H04L1/0003 ,  H04L1/0009 ,  H04N19/13 ,  H04N19/147 ,  H04N19/19

Abstract: A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method for compression includes receiving a first image and a first scheme as inputs for an autoencoder network; determining a first Lagrange multiplier based on the first scheme; and using the first image and the first Lagrange multiplier as inputs, computing a second image from the autoencoder network. The autoencoder network is trained using a plurality of Lagrange multipliers and a second image as training inputs.

公开(公告)号：US20230237355A1

公开(公告)日：2023-07-27

申请号：US18125897

申请日：2023-03-24

Applicant: Samsung Electronics Co., Ltd.

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

IPC: G06N7/01 ,  G06N20/00

CPC classification number: G06N7/01 ,  G06N20/00 ,  G06N5/04

Abstract: A method and system are herein disclosed. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables; generating a variational posterior of the joint latent variable model; training the variational posterior; performing inference of the first variable from the second variable based on the variational posterior, wherein performing the inference comprises conditionally generating the first variable from the second variable; and extracting common information between the first variable and the second variable, wherein extracting the common information comprises adding a regularization term to a loss function.

公开(公告)号：US11645869B2

公开(公告)日：2023-05-09

申请号：US16808357

申请日：2020-03-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Arvind Yedla ,  Marcel Nassar ,  Jungwon Lee

IPC: G06V40/16 ,  G06T7/70

CPC classification number: G06V40/168 ,  G06T7/70 ,  G06V40/161 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A system to recognize objects in an image includes an object detection network outputs a first hierarchical-calculated feature for a detected object. A face alignment regression network determines a regression loss for alignment parameters based on the first hierarchical-calculated feature. A detection box regression network determines a regression loss for detected boxes based on the first hierarchical-calculated feature. The object detection network further includes a weighted loss generator to generate a weighted loss for the first hierarchical-calculated feature, the regression loss for the alignment parameters and the regression loss of the detected boxes. A backpropagator backpropagates the generated weighted loss. A grouping network forms, based on the first hierarchical-calculated feature, the regression loss for the alignment parameters and the bounding box regression loss, at least one of a box grouping, an alignment parameter grouping, and a non-maximum suppression of the alignment parameters and the detected boxes.