中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

48 records (took 0.029 seconds)

    METHOD AND APPARATUS WITH HYPERPARAMETER SEARCHING FOR NEURAL NETWORK LEARNING
    1.
    发明公开
    METHOD AND APPARATUS WITH HYPERPARAMETER SEARCHING FOR NEURAL NETWORK LEARNING 审中-公开

    公开(公告)号：US20240242090A1

    公开(公告)日：2024-07-18

    申请号：US18477139

    申请日：2023-09-28

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Sung-Jae CHO ,  Changyong SON ,  Jongseok KIM ,  Jonghoon YOON

    IPC: G06N3/0985

    CPC classification number: G06N3/0985

    Abstract: A method of searching for hyperparameters for neural network learning includes: obtaining a preset early stop point; determining whether a current trial, among trials for searching for different combinations of hyperparameters, corresponds to a dry run trial; in response to a determination that the current trial corresponds to a dry run trial: executing learning epochs belonging to the current trial; searching for a combination of hyperparameters assigned to the current trial according to a result of the executing of the learning epochs; and changing the early stop point by based on whether an early stop with respect to a found combination of the hyperparameters is a success in each of the learning epochs.

    CONVOLUTIONAL NEURAL NETWORK (CNN) PROCESSING METHOD AND APPARATUS
    2.
    发明申请
    CONVOLUTIONAL NEURAL NETWORK (CNN) PROCESSING METHOD AND APPARATUS 有权

    公开(公告)号：US20230051648A1

    公开(公告)日：2023-02-16

    申请号：US17975837

    申请日：2022-10-28

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Jinwoo SON ,  Changyong SON ,  Jaejoon HAN ,  Chang Kyu CHOI

    IPC: G06N3/04 ,  G06N3/08

    Abstract: Disclosed is a convolutional neural network (CNN) processing apparatus and method, the apparatus configured to determine a loading space unit for at least one loading space in an input based on a height or a width for an input feature map of the input and an extent of a dimension of a kernel feature map, load target input elements corresponding to a target loading space, among the at least one loading space, from a memory and store the target input elements in an allocated input buffer having a size corresponding to the loading space unit, and perform a convolution operation between the target input elements stored in the input buffer and at least one kernel element of a kernel.

    NEURAL NETWORK METHOD AND APPARATUS
    4.
    发明申请
    NEURAL NETWORK METHOD AND APPARATUS 有权

    公开(公告)号：US20220138576A1

    公开(公告)日：2022-05-05

    申请号：US17574408

    申请日：2022-01-12

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Changyong SON ,  Jinwoo SON ,  Byungin YOO ,  Chang Kyu CHOI ,  Jae-Joon HAN

    IPC: G06N3/08 ,  G06F5/01 ,  G06N3/063 ,  G06F7/523 ,  G06N3/04

    Abstract: A lightened neural network method and apparatus. The neural network apparatus includes a processor configured to generate a neural network with a plurality of layers including plural nodes by applying lightened weighted connections between neighboring nodes in neighboring layers of the neural network to interpret input data applied to the neural network, wherein lightened weighted connections of at least one of the plurality of layers includes weighted connections that have values equal to zero for respective non-zero values whose absolute values are less than an absolute value of a non-zero value. The lightened weighted connections also include weighted connections that have values whose absolute values are no greater than an absolute value of another non-zero value, the lightened weighted connections being lightened weighted connections of trained final weighted connections of a trained neural network whose absolute maximum values are greater than the absolute value of the other non-zero value.

    FACE VERIFICATION METHOD AND APPARATUS
    6.
    发明申请
    FACE VERIFICATION METHOD AND APPARATUS 有权

    公开(公告)号：US20210089755A1

    公开(公告)日：2021-03-25

    申请号：US17111912

    申请日：2020-12-04

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Changyong SON ,  Wonsuk CHANG ,  Deoksang KIM ,  Dae-Kyu SHIN ,  Byungin YOO ,  Seungju HAN ,  Jaejoon HAN ,  Jinwoo SON ,  Chang Kyu CHOI

    IPC: G06K9/00 ,  G06K9/78 ,  G06K9/62

    Abstract: Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold.

    NEURAL NETWORK METHOD AND APPARATUS
    8.
    发明申请
    NEURAL NETWORK METHOD AND APPARATUS 审中-公开

    公开(公告)号：US20180032866A1

    公开(公告)日：2018-02-01

    申请号：US15630610

    申请日：2017-06-22

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Changyong SON ,  Jinwoo SON ,  Byungin YOO ,  Chang Kyu CHOI ,  Jae-Joon HAN

    IPC: G06N3/08 ,  G06F7/523 ,  G06F5/01 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06F5/01 ,  G06F7/523 ,  G06N3/04 ,  G06N3/063 ,  G06N3/082

    Abstract: A lightened neural network method and apparatus. The neural network apparatus includes a processor configured to generate a neural network with a plurality of layers including plural nodes by applying lightened weighted connections between neighboring nodes in neighboring layers of the neural network to interpret input data applied to the neural network, wherein lightened weighted connections of at least one of the plurality of layers includes weighted connections that have values equal to zero for respective non-zero values whose absolute values are less than an absolute value of a non-zero value. The lightened weighted connections also include weighted connections that have values whose absolute values are no greater than an absolute value of another non-zero value, the lightened weighted connections being lightened weighted connections of trained final weighted connections of a trained neural network whose absolute maximum values are greater than the absolute value of the other non-zero value.

Patent Agency Ranking