利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.013 秒)

    Machine learning method and machine learning device
    3.
    发明授权
    Machine learning method and machine learning device 有权

    公开(公告)号：US11663462B2

    公开(公告)日：2023-05-30

    申请号：US16030859

    申请日：2018-07-10

    申请人： National Central University

    发明人： Jia-Ching Wang ,  Chien-Yao Wang ,  Chih-Hsuan Yang

    IPC分类号： G06N3/08 ,  G06N3/04

    CPC分类号： G06N3/08 ,  G06N3/04

    摘要： A machine learning method and a machine learning device are provided. The machine learning method includes: receiving an input signal and performing normalization on the input signal; transmitting the normalized input signal to a convolutional layer; and adding a sparse coding layer after the convolutional layer, wherein the sparse coding layer uses dictionary atoms to reconstruct signals on a projection of the normalized input signal passing through the convolutional layer, and the sparse coding layer receives a mini-batch input to refresh the dictionary atoms.

    Method for repairing incomplete 3D depth image using 2D image information
    4.
    发明授权
    Method for repairing incomplete 3D depth image using 2D image information 有权

    公开(公告)号：US10685474B2

    公开(公告)日：2020-06-16

    申请号：US16194847

    申请日：2018-11-19

    申请人： NATIONAL CENTRAL UNIVERSITY

    发明人： Yeh-Wei Yu ,  Chi-Chung Lau ,  Ching-Cherng Sun ,  Tsung-Hsun Yang ,  Tzu-Kai Wang ,  Jia-Ching Wang ,  Chien-Yao Wang ,  Kuan-Chung Wang

    IPC分类号： G06T15/04 ,  G06T19/20

    摘要： The present invention provides a method for repairing incomplete 3D depth image using 2D image information. The method includes the following steps: obtaining 2D image information and 3D depth image information; dividing 2D image information into 2D reconstruction blocks and 2D reconstruction boundaries, and corresponding to 3D reconstruction of blocks and 3D reconstruction boundaries; analyzing each 3D reconstruction block, partitioning into residual-surface blocks and repaired blocks; and proceeding at least one 3D image reconstruction, which extends with the initial depth value of the 3D depth image of each of the residual-surface block and covers all the corresponding repaired block to form a repair block and to achieve the purpose of repairing incomplete 3D depth images using 2D image information.

    Vision-aided hearing assisting device
    6.
    发明授权
    Vision-aided hearing assisting device 有权
    视力辅助助听器

    公开(公告)号：US09280914B2

    公开(公告)日：2016-03-08

    申请号：US14249362

    申请日：2014-04-10

    申请人： National Central University

    发明人： Jia-Ching Wang ,  Chang-Hong Lin ,  Chih-Hao Shih

    IPC分类号： G09B21/00 ,  G10L21/10

    CPC分类号： G09B21/009 ,  G10L21/10

    摘要： The present invention discloses a vision-aided hearing assisting device, which includes a display device, a microphone and a processing unit. The processing unit includes a receiving module, a message generating module and a display driving module. The processing unit is electrically connected to the display device and the microphone. The receiving module receives a surrounding sound signal, which is generated by the microphone. The message generating module analyzes the surrounding sound signal according to a present-scenario mode to generate a related message related with the surrounding sound signal. The display driving module drives the display device to display the related message.

    摘要翻译： 本发明公开了一种视觉辅助听力辅助装置，其包括显示装置，麦克风和处理单元。 处理单元包括接收模块，消息产生模块和显示驱动模块。 处理单元电连接到显示装置和麦克风。 接收模块接收由麦克风产生的周围声音信号。 消息产生模块根据当前场景模式分析周围的声音信号，以产生与周围声音信号相关的相关消息。 显示驱动模块驱动显示装置显示相关消息。

    Computing device and method for generating machine translation model and machine-translation device
    7.
    发明授权
    Computing device and method for generating machine translation model and machine-translation device 有权

    公开(公告)号：US11520997B2

    公开(公告)日：2022-12-06

    申请号：US16699477

    申请日：2019-11-29

    申请人： National Central University

    发明人： Jia-Ching Wang ,  Yi-Xing Lin

    IPC分类号： G06F40/58 ,  G06F40/242 ,  G06N20/00

    摘要： A device and a method for generating a machine translation model and a machine translation device are disclosed. The device inputs a source training sentence of a source language and a dictionary data to a generator network so that the generator network outputs a target training sentence of a target language according to the source training sentence and the dictionary data. Then, the device inputs the target training sentence and a correct translation of the source training sentence to a discriminator network so as to calculate an error between the target training sentence and the correct translation according to the output of the discriminator network, and trains the generator network and the discriminator network respectively. The trained generator network is the machine translation model.

    MACHINE LEARNING METHOD AND MACHINE LEARNING DEVICE
    10.
    发明申请
    MACHINE LEARNING METHOD AND MACHINE LEARNING DEVICE 审中-公开

    公开(公告)号：US20200012932A1

    公开(公告)日：2020-01-09

    申请号：US16030859

    申请日：2018-07-10

    申请人： National Central University

    发明人： Jia-Ching Wang ,  Chien-Yao Wang ,  Chih-Hsuan Yang

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： A machine learning method and a machine learning device are provided. The machine learning method includes: receiving an input signal and performing normalization on the input signal; transmitting the normalized input signal to a convolutional layer; and adding a sparse coding layer after the convolutional layer, wherein the sparse coding layer uses dictionary atoms to reconstruct signals on a projection of the normalized input signal passing through the convolutional layer, and the sparse coding layer receives a mini-batch input to refresh the dictionary atoms.