中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

38 records (took 0.021 seconds)

    METHOD AND APPARATUS FOR REDUCING COMPUTATIONAL COMPLEXITY OF CONVOLUTIONAL NEURAL NETWORKS
    21.
    发明申请
    METHOD AND APPARATUS FOR REDUCING COMPUTATIONAL COMPLEXITY OF CONVOLUTIONAL NEURAL NETWORKS 审中-公开

    公开(公告)号：US20180300624A1

    公开(公告)日：2018-10-18

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

    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.

    Computing system with channel estimation mechanism and method of operation thereof
    23.
    发明授权
    Computing system with channel estimation mechanism and method of operation thereof 有权
    具有信道估计机制的计算系统及其操作方法

    公开(公告)号：US09596102B2

    公开(公告)日：2017-03-14

    申请号：US14553917

    申请日：2014-11-25

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yoo Jin Choi ,  Jung Hyun Bae ,  Jungwon Lee ,  Inyup Kang

    IPC: H04L25/02 ,  H04L5/00 ,  H04L27/26

    CPC classification number: H04L25/022 ,  H04L5/0051 ,  H04L25/021 ,  H04L27/2613 ,  H04L27/2647

    Abstract: A computing system includes: an inter-device interface configured to receive receiver signal for communicating serving content through a communication channel; a communication unit, coupled to the inter-device interface, configured to: calculate a weighting set corresponding to a modular estimation mechanism, and generate a channel estimate based on the weighting set for characterizing the communication channel for recovering the serving content.

    Abstract translation: 计算系统包括：设备间接口，被配置为接收通过通信信道传送服务内容的接收机信号; 耦合到所述设备间接口的通信单元，被配置为：计算对应于模块化估计机制的加权集合，并且基于所述加权集合生成用于表征所述通信信道以恢复所述服务内容的信道估计。

    METHOD AND APPARATUS FOR DATA-FREE POST-TRAINING NETWORK QUANTIZATION AND GENERATING SYNTHETIC DATA BASED ON A PRE-TRAINED MACHINE LEARNING MODEL
    24.
    发明申请
    METHOD AND APPARATUS FOR DATA-FREE POST-TRAINING NETWORK QUANTIZATION AND GENERATING SYNTHETIC DATA BASED ON A PRE-TRAINED MACHINE LEARNING MODEL 有权

    公开(公告)号：US20250086457A1

    公开(公告)日：2025-03-13

    申请号：US18957380

    申请日：2024-11-22

    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, and {circumflex over (μ)}ψ 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.

    Method and apparatus for reducing computational complexity of convolutional neural networks
    25.
    发明授权
    Method and apparatus for reducing computational complexity of convolutional neural networks 有权

    公开(公告)号：US12248866B2

    公开(公告)日：2025-03-11

    申请号：US17473813

    申请日：2021-09-13

    Applicant: Samsung Electronics Co., Ltd.

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

    IPC: G06N3/06 ,  G06N3/04 ,  G06N3/0464 ,  G06N3/08 ,  G06F5/01 ,  G06F17/16

    Abstract: A convolutional neural network (CNN) system for generating a classification for an input image is presented. The CNN system comprises circuitry running on clock cycles and configured to compute a product of two received values, and at least one non-transitory computer-readable medium that stores instructions for the circuitry 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 an element at an index of the at least one selection to zero and cyclic shifting a puncture pattern to achieve a 1/d reduction in number of clock cycles, where d is an integer and puncture interval value >1. The feature map is convolved with the kernel to generate an output, and a classification of the input image is generated based on the output.

    METHOD AND APPARATUS FOR DATA-FREE POST-TRAINING NETWORK QUANTIZATION AND GENERATING SYNTHETIC DATA BASED ON A PRE-TRAINED MACHINE LEARNING MODEL
    26.
    发明申请
    METHOD AND APPARATUS FOR DATA-FREE POST-TRAINING NETWORK QUANTIZATION AND GENERATING SYNTHETIC DATA BASED ON A PRE-TRAINED MACHINE LEARNING MODEL 有权

    公开(公告)号：US20220083855A1

    公开(公告)日：2022-03-17

    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 ,  G06N3/04 ,  G06K9/62 ,  G06F17/18 ,  G06N7/00

    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.

    METHOD AND APPARATUS FOR REDUCING COMPUTATIONAL COMPLEXITY OF CONVOLUTIONAL NEURAL NETWORKS
    27.
    发明申请
    METHOD AND APPARATUS FOR REDUCING COMPUTATIONAL COMPLEXITY OF CONVOLUTIONAL NEURAL NETWORKS 有权

    公开(公告)号：US20210406647A1

    公开(公告)日：2021-12-30

    申请号：US17473813

    申请日：2021-09-13

    Applicant: Samsung Electronics Co., Ltd.

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

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

    Abstract: A convolutional neural network (CNN) system for generating a classification for an input image is presented. The CNN system comprises circuitry running on clock cycles and configured to compute a product of two received values, and at least one non-transitory computer-readable medium that stores instructions for the circuitry 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 an element at an index of the at least one selection to zero and cyclic shifting a puncture pattern to achieve a 1/d reduction in number of clock cycles, where d is an integer and puncture interval value>1. The feature map is convolved with the kernel to generate an output, and a classification of the input image is generated based on the output.

    System and method for frequency estimation bias removal
    28.
    发明授权
    System and method for frequency estimation bias removal 有权

    公开(公告)号：US10355792B2

    公开(公告)日：2019-07-16

    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: H04B1/10 ,  H04B17/336 ,  H04L27/148 ,  H04L27/10 ,  H04B17/21

    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.

Patent Agency Ranking