利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

24 条记录 (耗时 0.034 秒)

    DEVICE AND METHOD FOR MULTI-TASK LEARNING AND A TESTING DEVICE AND TESTING METHOD USING SAME
    8.
    发明公开
    DEVICE AND METHOD FOR MULTI-TASK LEARNING AND A TESTING DEVICE AND TESTING METHOD USING SAME 审中-公开

    公开(公告)号：US20240312189A1

    公开(公告)日：2024-09-19

    申请号：US18244680

    申请日：2023-09-11

    申请人： HYUNDAI MOTOR COMPANY ,  KIA CORPORATION

    发明人： Jae Hoon Cho ,  Hyun Kook Park

    IPC分类号： G06V10/774 ,  G06V10/77 ,  G06V10/776

    CPC分类号： G06V10/774 ,  G06V10/7715 ,  G06V10/776

    摘要： A multi-task learning device includes a feature extraction layer that generates a first feature corresponding to a first image and a second feature corresponding to a second image; a first decoding layer that generates a first task inference result corresponding to the first image; a second decoding layer that generates a second task inference result corresponding to the second image; a first loss layer that generates a first task loss with reference to the first task inference result and a first task ground truth (GT) result corresponding to the first task inference result; a second loss layer that generates a second task loss with reference to the second task inference result and a second task GT result corresponding to the second task inference result; a feature loss layer that generates a feature loss with reference to the first feature and the second feature; and a parameter updater that updates parameters of at least some of the various layers.

    LEARNING DEVICE AND TEST DEVICE FOR TRAINING STUDENT NEURAL NETWORK
    9.
    发明公开
    LEARNING DEVICE AND TEST DEVICE FOR TRAINING STUDENT NEURAL NETWORK 审中-公开

    公开(公告)号：US20240303467A1

    公开(公告)日：2024-09-12

    申请号：US18507548

    申请日：2023-11-13

    申请人： Hyundai Motor Company ,  Kia Corporation

    发明人： Jae Hoon Cho ,  Jae Hyeon Park ,  Hyun Kook Park

    IPC分类号： G06N3/045 ,  G06N3/084 ,  G06V10/776 ,  G06V10/778 ,  G06V10/82 ,  G06V20/70

    CPC分类号： G06N3/045 ,  G06N3/084 ,  G06V10/776 ,  G06V10/7792 ,  G06V10/82 ,  G06V20/70

    摘要： Machine learning and testing devices are provided. The device applies a neural network operation of a first student neural network to a training image to generate first prediction information, applies a neural network operation of a second student neural network to generate second prediction information, applies an error identification operation to a first integrated image to generate first error identification prediction information, applies the error identification operation to a second integrated image to generate second error identification prediction information, applies a network operation of a first teacher neural network to the training image to generate first pseudo label information, applies a neural network operation of a second teacher neural network to the training image to generate second pseudo label information, back-propagates a loss and updates parameters of the first and second student neural networks.