利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

129 条记录 (耗时 0.048 秒)

    METHODS OF TRAINING DEEP LEARNING MODEL AND PREDICTING CLASS AND ELECTRONIC DEVICE FOR PERFORMING THE METHODS
    7.
    发明公开
    METHODS OF TRAINING DEEP LEARNING MODEL AND PREDICTING CLASS AND ELECTRONIC DEVICE FOR PERFORMING THE METHODS 审中-公开

    公开(公告)号：US20230177331A1

    公开(公告)日：2023-06-08

    申请号：US18060405

    申请日：2022-11-30

    申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    发明人： Young Ho JEONG ,  Soo Young PARK ,  Tae Jin LEE

    IPC分类号： G06N3/08

    CPC分类号： G06N3/08

    摘要： Disclosed are methods of training a deep learning model and predicting a class and an electronic device for performing the methods. A method of training a deep learning model may include identifying training data labeled for each class, determining whether to augment the training data based on overall recognition performance indicating prediction accuracy of the deep learning model calculated in a previous epoch, augmenting the training data based on class-specific recognition performance indicating class-specific prediction accuracy of the deep learning model calculated in the previous epoch, predicting a class by inputting the training data or the training data that is augmented to the deep learning model according to a determination of whether to augment the training data, and training the deep learning model based on a labeled class and the predicted class.

    METHODS OF ENCODING AND DECODING, ENCODER AND DECODER PERFORMING THE METHODS
    8.
    发明申请
    METHODS OF ENCODING AND DECODING, ENCODER AND DECODER PERFORMING THE METHODS 有权

    公开(公告)号：US20230048402A1

    公开(公告)日：2023-02-16

    申请号：US17884364

    申请日：2022-08-09

    申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    发明人： Jongmo SUNG ,  Seung Kwon BEACK ,  Tae Jin LEE ,  Woo-taek KIM ,  Inseon JANG

    IPC分类号： G10L19/06 ,  G06N3/04

    摘要： Provided is an encoding method according to various example embodiments and an encoder performing the method. The encoding method includes outputting a linear prediction(LP) coefficients bitstream and a residual signal by performing a linear prediction analysis on an input signal, outputting a first latent signal obtained by encoding a periodic component of the residual signal, using a first neural network module, outputting a first bitstream obtained by quantizing the first latent signal, using a quantization module, outputting a second latent signal obtained by encoding an aperiodic component of the residual signal, using the first neural network module, and outputting a second bitstream obtained by quantizing the second latent signal, using the quantization module, wherein the aperiodic component of the residual signal is calculated based on a periodic component of the residual signal decoded from the quantized first latent signal output by de-quantizing the first bitstream.