中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

38 records (took 0.026 seconds)

    Method and apparatus for learning stochastic inference models between multiple random variables with unpaired data
    32.
    发明授权
    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

    Applicant: Samsung Electronics Co., Ltd.

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

    IPC: G06N20/20 ,  G06N3/088 ,  G06N3/04

    Abstract: 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.

    Method and apparatus for reducing computational complexity of convolutional neural networks
    33.
    发明授权
    Method and apparatus for reducing computational complexity of convolutional neural networks 有权

    公开(公告)号：US11164071B2

    公开(公告)日：2021-11-02

    申请号：US15634537

    申请日：2017-06-27

    Applicant: Samsung Electronics Co., Ltd.

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

    IPC: G06N3/06 ,  G06N3/08 ,  G06N3/04 ,  G06F5/01 ,  G06F17/16

    Abstract: Disclosed herein is convolutional neural network (CNN) system for generating a classification for an input image. According to an embodiment, the CNN system comprises a sequence of neural network layers configured to: derive a feature map based on at least the input image; puncture at least one selection among the feature map and a kernel by setting the value of one or more elements of a row of the at least one selection to zero according to a pattern and cyclic shifting the pattern by a predetermined interval per row to set the value of one or more elements of the rest of the rows of the at least one selection according to the cyclic shifted pattern; convolve the feature map with the kernel to generate a first convolved output; and generate the classification for the input image based on at least the first convolved output.

    METHOD AND APPARATUS FOR LEARNING STOCHASTIC INFERENCE MODELS BETWEEN MULTIPLE RANDOM VARIABLES WITH UNPAIRED DATA
    34.
    发明申请
    METHOD AND APPARATUS FOR LEARNING STOCHASTIC INFERENCE MODELS BETWEEN MULTIPLE RANDOM VARIABLES WITH UNPAIRED DATA 有权

    公开(公告)号：US20210319326A1

    公开(公告)日：2021-10-14

    申请号：US16886429

    申请日：2020-05-28

    Applicant: Samsung Electronics Co., Ltd.

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

    IPC: G06N3/08 ,  G06N3/04

    Abstract: 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.

    Computing system with power estimation mechanism and method of operation thereof
    36.
    发明授权
    Computing system with power estimation mechanism and method of operation thereof 有权
    具有功率估计机制的计算系统及其操作方法

    公开(公告)号：US09312968B2

    公开(公告)日：2016-04-12

    申请号：US14297327

    申请日：2014-06-05

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yoo Jin Choi ,  Dongwoon Bai ,  Jungwon Lee ,  Inyup Kang

    IPC: H03M5/02 ,  H04B17/345 ,  H04L25/06

    CPC classification number: H04B17/345 ,  H04L25/067

    Abstract: A computing system includes: an antenna configured to receive a receiver signal for representing a serving signal and an interference signal; a communication unit, coupled to the antenna, configured to: calculate a signal likelihood from the receiver signal based on a Gaussian approximation mechanism; calculate an interference power estimate based on the signal likelihood for characterizing the interference signal; and estimating the serving signal based on the interference power estimate.

    Abstract translation: 计算系统包括：天线，被配置为接收用于表示服务信号和干扰信号的接收机信号; 耦合到所述天线的通信单元，被配置为：基于高斯近似机制从所述接收机信号计算信号似然性; 基于用于表征干扰信号的信号可能性来计算干扰功率估计; 以及基于所述干扰功率估计来估计所述服务信号。

    COMPUTING SYSTEM WITH INTERFERENCE CLASSIFICATION MECHANISM AND METHOD OF OPERATION THEREOF
    37.
    发明申请
    COMPUTING SYSTEM WITH INTERFERENCE CLASSIFICATION MECHANISM AND METHOD OF OPERATION THEREOF 有权
    具有干扰分类机制的计算系统及其操作方法

    公开(公告)号：US20140362958A1

    公开(公告)日：2014-12-11

    申请号：US14297377

    申请日：2014-06-05

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yoo Jin Choi ,  Dongwoon Bai ,  Jungwon Lee ,  Inyup Kang

    IPC: H04L25/03 ,  H04L27/00

    CPC classification number: H04L25/03006 ,  H04B1/10 ,  H04B15/00 ,  H04L25/021 ,  H04L25/03993 ,  H04L27/0012

    Abstract: A computing system includes: an antenna configured to receive a receiver signal for representing a serving signal and an interference signal; a communication unit, coupled to the antenna, configured to: calculate a decoding result based on the receiver signal, generate an interference modulation estimate based on the decoding result and the receiver signal, and calculate a content result based on the interference modulation estimate for representing the serving signal.

    Abstract translation: 计算系统包括：天线，被配置为接收用于表示服务信号和干扰信号的接收机信号; 耦合到所述天线的通信单元，被配置为：基于所述接收机信号来计算解码结果，基于所述解码结果和所述接收机信号生成干扰调制估计，并基于所述干扰调制估计来计算内容结果， 服务信号。

    COMPUTING SYSTEM WITH POWER ESTIMATION MECHANISM AND METHOD OF OPERATION THEREOF
    38.
    发明申请
    COMPUTING SYSTEM WITH POWER ESTIMATION MECHANISM AND METHOD OF OPERATION THEREOF 有权
    具有功率估计机制的计算系统及其运行方法

    公开(公告)号：US20140362954A1

    公开(公告)日：2014-12-11

    申请号：US14297327

    申请日：2014-06-05

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yoo Jin Choi ,  Dongwoon Bai ,  Jungwon Lee ,  Inyup Kang

    IPC: H04L1/00

    CPC classification number: H04B17/345 ,  H04L25/067

    Abstract: A computing system includes: an antenna configured to receive a receiver signal for representing a serving signal and an interference signal; a communication unit, coupled to the antenna, configured to: calculate a signal likelihood from the receiver signal based on a Gaussian approximation mechanism; calculate an interference power estimate based on the signal likelihood for characterizing the interference signal; and estimating the serving signal based on the interference power estimate.

    Abstract translation: 计算系统包括：天线，被配置为接收用于表示服务信号和干扰信号的接收机信号; 耦合到所述天线的通信单元，被配置为：基于高斯近似机制从所述接收机信号计算信号似然性; 基于用于表征干扰信号的信号可能性来计算干扰功率估计; 以及基于所述干扰功率估计来估计所述服务信号。

Patent Agency Ranking