专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US09504042B2 System and method for encoding and decoding of data with channel polarization mechanism 有权
标题翻译：用信道极化机制对数据进行编码和解码的系统和方法
公开(公告)号：US09504042B2
公开(公告)日：2016-11-22
申请号：US14522924
申请日：2014-10-24
申请人： Samsung Electronics Co., Ltd.
发明人： Mostafa El-Khamy , Hessam Mahdavifar , Gennady Feygin , Jungwon Lee , Inyup Kang
IPC分类号： H04B7/216 , H04W72/04 , H03M13/13 , H04W28/06
CPC分类号： H04W72/0466 , H03M13/13 , H03M13/353 , H04W28/06
摘要： A computing system includes: a communication unit configured to: determine a relaxed coding profile including a polar-processing range for processing content data over a bit channel; process the content data based on a total polarization level being within the polar-processing range, the polar-processing range for controlling a polar processing mechanism or a portion therein corresponding to the bit channel for the content data; and an inter-device interface, coupled to the communication unit, configured to communicate the content data.
摘要翻译：计算系统包括：通信单元，被配置为：确定包括通过位信道处理内容数据的极化处理范围的松弛编码简档; 基于在极化处理范围内的总极化电平处理内容数据，用于控制极性处理机制的极化处理范围或其中对应于内容数据的比特信道的部分; 以及耦合到所述通信单元的被配置为传送所述内容数据的设备间接口。

22. 发明申请

US20160065245A1 ELECTRONIC SYSTEM WITH VITERBI DECODER MECHANISM AND METHOD OF OPERATION THEREOF 审中-公开
标题翻译：具有VITERBI解码器机构的电子系统及其操作方法
公开(公告)号：US20160065245A1
公开(公告)日：2016-03-03
申请号：US14706388
申请日：2015-05-07
申请人： Samsung Electronics Co., Ltd.
发明人： Marcel Nassar , Mostafa El-Khamy , Inyup Kang , Jungwon Lee
IPC分类号： H03M13/41 , H03M13/25
CPC分类号： H03M13/413 , H03M13/395 , H03M13/4107 , H03M13/4115
摘要： A electronic system includes: a support chip configured to receive an input code stream; a circular Viterbi mechanism, coupled to the support chip, configured to: generate a final path metric for the input code stream, store intermediate path metrics at the repetition depth, generate a repetition path metric for the input code stream, and calculate a soft correlation metric based on the final path metric, the repetition path metric, and the intermediate path metrics.
摘要翻译：电子系统包括：被配置为接收输入码流的支持芯片; 耦合到所述支持芯片的循环维特比机构，被配置为：为所述输入代码流生成最终路径度量，在所述重复深度处存储中间路径量度，生成所述输入代码流的重复路径度量，并计算软相关基于最终路径度量，重复路径度量和中间路径度量的度量。

23. 发明申请

US20140208183A1 METHOD AND SYSTEM FOR ENCODING AND DECODING DATA USING CONCATENATED POLAR CODES 有权
标题翻译：使用相关极性代码编码和解码数据的方法和系统
公开(公告)号：US20140208183A1
公开(公告)日：2014-07-24
申请号：US14158571
申请日：2014-01-17
申请人： Samsung Electronics Co., Ltd.
发明人： Hessam Mahdavifar , Mostafa El-Khamy , Jungwon Lee , Inyup Kang
IPC分类号： H03M13/29
CPC分类号： H03M13/296 , H03M13/1102 , H03M13/13 , H03M13/1515 , H03M13/27 , H03M13/2707 , H04L1/0041 , H04L1/0065
摘要： 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.
摘要翻译：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。

24. 发明授权

US12073847B2 System and method for acoustic echo cancelation using deep multitask recurrent neural networks 有权
公开(公告)号：US12073847B2
公开(公告)日：2024-08-27
申请号：US17827424
申请日：2022-05-27
申请人： Samsung Electronics Co., Ltd.
发明人： Amin Fazeli , Mostafa El-Khamy , Jungwon Lee
IPC分类号： G10L21/0232 , G06N3/08 , G06N20/10 , G10L21/0208 , H04R3/04
CPC分类号： G10L21/0232 , G06N3/08 , G06N20/10 , H04R3/04 , G10L2021/02082
摘要： 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.

25. 发明授权

US12051237B2 Multi-expert adversarial regularization for robust and data-efficient deep supervised learning 有权
公开(公告)号：US12051237B2
公开(公告)日：2024-07-30
申请号：US17674832
申请日：2022-02-17
申请人： Samsung Electronics Co., Ltd.
发明人： Behnam Babagholami Mohamadabadi , Qingfeng Liu , Mostafa El-Khamy , Jungwon Lee
IPC分类号： G06V10/82 , G06N5/04 , G06V10/774 , G06V10/776 , G06V10/778
CPC分类号： G06V10/82 , G06N5/04 , G06V10/774 , G06V10/776 , G06V10/7784
摘要： A system and a method to train a neural network are disclosed. A first image is weakly and strongly augmented. The first image, the weakly and strongly augmented first images are input into a feature extractor to obtain augmented features. Each weakly augmented first image is input to a corresponding first expert head to determine a supervised loss for each weakly augmented first image. Each strongly augmented first image is input to a corresponding second expert head to determine a diversity loss for each strongly augmented first image. The feature extractor is trained to minimize the supervised loss on weakly augmented first images and to minimize a multi-expert consensus loss on strongly augmented first images. Each first expert head is trained to minimize the supervised loss for each weakly augmented first image, and each second expert head is trained to minimize the diversity loss for each strongly augmented first image.

26. 发明授权

US11900234B2 System and method for designing efficient super resolution deep convolutional neural networks by cascade network training, cascade network trimming, and dilated convolutions 有权
公开(公告)号：US11900234B2
公开(公告)日：2024-02-13
申请号：US17007739
申请日：2020-08-31
申请人： Samsung Electronics Co., Ltd.
发明人： Haoyu Ren , Mostafa El-Khamy , Jungwon Lee
IPC分类号： G06N20/00 , G06N3/04 , G06N3/08 , G06N3/082 , G06N3/045
CPC分类号： G06N3/04 , G06N3/045 , G06N3/08 , G06N3/082 , G06N20/00
摘要： Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.

27. 发明授权

US11847826B2 System and method for providing dominant scene classification by semantic segmentation 有权
公开(公告)号：US11847826B2
公开(公告)日：2023-12-19
申请号：US18083081
申请日：2022-12-16
申请人： Samsung Electronics Co., Ltd.
发明人： Qingfeng Liu , Mostafa El-Khamy , Rama Mythili Vadali , Tae-ui Kim , Andrea Kang , Dongwoon Bai , Jungwon Lee , Maiyuran Wijay , Jaewon Yoo
IPC分类号： G06T7/00 , G06V20/00 , G06V20/10 , G06F18/24 , H04N23/61 , H04N23/667 , G06V10/764 , G06V10/82 , G06V10/26 , G06V10/50
CPC分类号： G06V20/35 , G06F18/24 , G06V10/26 , G06V10/50 , G06V10/764 , G06V10/82 , G06V20/10 , H04N23/61 , H04N23/667
摘要： A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map being labeled with a plurality of corresponding classes of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; and outputting a detected dominant class of the scene based on a plurality of ranked labels based on the area ratios.

28. 发明授权

US11699070B2 Method and apparatus for providing rotational invariant neural networks 有权
公开(公告)号：US11699070B2
公开(公告)日：2023-07-11
申请号：US16452005
申请日：2019-06-25
申请人： Samsung Electronics Co., Ltd.
发明人： Mostafa El-Khamy , Jungwon Lee , Yoo Jin Choi , Haoyu Ren
IPC分类号： G06N3/08 , G06N20/10 , G06F18/214 , G06V10/82 , G06V10/44 , G06V10/46
CPC分类号： G06N3/08 , G06F18/214 , G06N20/10 , G06V10/454 , G06V10/462 , G06V10/82
摘要： A method and apparatus for providing a rotational invariant neural network is herein disclosed. According to one embodiment, a method includes receiving a first input of an image in a first orientation and training a kernel to be symmetric such that an output corresponding to the first input is the same as an output corresponding to a second input of the image in a second orientation.

29. 发明授权

US11687780B2 Method and apparatus for data efficient semantic segmentation 有权
公开(公告)号：US11687780B2
公开(公告)日：2023-06-27
申请号：US17241848
申请日：2021-04-27
申请人： Samsung Electronics Co., Ltd.
发明人： Qingfeng Liu , Mostafa El-Khamy , Jungwon Lee , Behnam Babagholami Mohamadabadi
IPC分类号： G06K9/62 , G06N3/08 , G06F18/2323 , G06F18/2415 , G06F18/2431 , G06V30/19 , G06V10/772 , G06V10/774 , G06V10/80 , G06F18/2321 , G06F18/25 , G06N3/045 , G06N3/04 , G06N5/022 , G06N5/025
CPC分类号： G06N3/08 , G06F18/2321 , G06F18/2323 , G06F18/2415 , G06F18/2431 , G06F18/253 , G06F18/254 , G06N3/04 , G06N3/045 , G06N5/022 , G06N5/025 , G06V10/772 , G06V10/774 , G06V10/806 , G06V10/809 , G06V30/1914 , G06V30/1918 , G06V30/19107 , G06V30/19147
摘要： A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.

30. 发明授权

US11615317B2 Method and apparatus for learning stochastic inference models between multiple random variables with unpaired data 有权
公开(公告)号：US11615317B2
公开(公告)日：2023-03-28
申请号：US16886429
申请日：2020-05-28
申请人： Samsung Electronics Co., Ltd.
发明人： Yoo Jin Choi , Jongha Ryu , Mostafa El-Khamy , Jungwon Lee , Young-Han Kim
IPC分类号： G06N20/20 , G06N3/088 , G06N3/04
摘要： A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式