知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.016 seconds)

    METHOD AND DEVICE FOR TRAINING NEURAL NETWORK
    11.
    发明申请
    METHOD AND DEVICE FOR TRAINING NEURAL NETWORK 有权

    公开(公告)号：US20210264260A1

    公开(公告)日：2021-08-26

    申请号：US17033088

    申请日：2020-09-25

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： BYEOUNGSU KIM ,  Kyoungyoung Kim ,  Jaegon Kim ,  Changgwun Lee ,  Sanghyuck Ha

    IPC: G06N3/08 ,  G06N3/04

    Abstract: The present disclosure relates to neural network training. The neural network training relates to a training method, a training device, and a system including the neural network. The neural network training includes extracting annotation data and first reliability values for first data using a neural network trained based on training data, selecting second data from among the first data based on the second data having second reliability values greater than or equal to a threshold value, expanding the training data based on the second data, and retraining the neural network based on the expanded training data

    Neural network system for performing learning, learning method thereof, and transfer learning method of neural network processor
    13.
    发明授权
    Neural network system for performing learning, learning method thereof, and transfer learning method of neural network processor 有权

    公开(公告)号：US11494646B2

    公开(公告)日：2022-11-08

    申请号：US16701841

    申请日：2019-12-03

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jaegon Kim ,  Sangsoo Ko ,  Kyoungyoung Kim ,  Byeoungsu Kim ,  Sanghyuck Ha

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A neural network system includes a processor and a memory. The processor is configured to perform learning including multiple learning iterations on multiple layers, to determine at least one layer in which the learning is interrupted among the multiple layers. The determination of the at least one layer in which the learning is interrupted is based on a result of comparing for each of the multiple layers a distribution of first weight values resulting from a first learning iteration with a distribution of second weight values resulting from a second learning iteration. The processor is also configured to perform a third learning iteration in layers except the at least one layer for which interruption of the learning has been determined. The memory stores first distribution information of the first weight values and second distribution information of the second weight values and is configured to provide the first distribution information and the second distribution information to the processor when the second learning iteration is completed.

Patent Agency Ranking