中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5875 records (took 0.045 seconds)

    Execution method, execution device, learning method, learning device, and recording medium for deep neural network
    492.
    发明授权
    Execution method, execution device, learning method, learning device, and recording medium for deep neural network 有权

    公开(公告)号：US11481613B2

    公开(公告)日：2022-10-25

    申请号：US16696005

    申请日：2019-11-26

    Applicant: Panasonic Intellectual Property Corporation of America

    Inventor： Denis A. Gudovskiy ,  Luca Rigazio

    IPC: G10L15/22 ,  G06N3/063 ,  G06N3/04 ,  G06N3/08

    Abstract: Executing a deep neural network by obtaining, during deep neural network inference, a binary intermediate feature map in binary representation by converting a floating-point or fixed-point intermediate feature map into a binary vector using a first transformation module; generating a compressed feature map by compressing the binary intermediate feature map using a nonlinear dimensionality reduction layer; storing the compressed feature map into memory; reconstructing the binary intermediate feature map by decompressing the compressed feature map read from the memory using a reconstruction layer corresponding to the nonlinear dimensionality reduction layer; and converting the reconstructed binary intermediate feature map into a floating-point or fixed-point intermediate feature map using a second transformation module.

    USER EQUIPMENT AND BASE STATION INVOLVED IN CONTROL CHANNEL SIGNALING
    493.
    发明申请
    USER EQUIPMENT AND BASE STATION INVOLVED IN CONTROL CHANNEL SIGNALING 有权

    公开(公告)号：US20220338178A1

    公开(公告)日：2022-10-20

    申请号：US17760721

    申请日：2020-10-28

    Applicant: Panasonic Intellectual Property Corporation of America

    Inventor： Quan KUANG ,  Hidetoshi SUZUKI ,  Hongchao LI ,  Rikin SHAH

    IPC: H04W72/04 ,  H04W16/14 ,  H04W76/28

    Abstract: The present disclosure relates to a user equipment (UE) that comprises a processor that operates a monitoring function that involves monitoring of a downlink control channel of an unlicensed radio cell based on one of a plurality of groups of search space sets (SSS). The unlicensed radio cell operates in an unlicensed spectrum and is controlled by a base station that is in communication with the user equipment. Further, one of the plurality of groups of SSSs is configured to be a default group of SSSs. The processor determines one group of the plurality of SSS groups for performing the monitoring function, depending on the downlink control channel. The monitoring function is not performed during a non-monitoring time period. The processor determines to perform the monitoring function based on the default group of SSSs, when performing the monitoring function subsequent to the non-monitoring time period.

    INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING SYSTEM
    496.
    发明申请
    INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING SYSTEM 有权

    公开(公告)号：US20220327563A1

    公开(公告)日：2022-10-13

    申请号：US17850168

    申请日：2022-06-27

    Applicant: Panasonic Intellectual Property Corporation of America

    Inventor： Hirokazu KAWAMOTO ,  Eiichi MURAMOTO ,  Masayoshi TOJIMA

    IPC: G06Q30/02 ,  G06Q10/06

    Abstract: An information processing method includes: obtaining first simulation results by running a simulation according to an operating parameter of a mobile object before and after a first change; evaluating each first simulation result based on risk, cost, and value indexes in an operation of the mobile object to obtain first evaluation results; calculating a first influence degree of the operating parameter on each index using sets of the operating parameters and the first evaluation results corresponding to the first simulation results; applying a second change to the operating parameter based on a simulation search policy and the first influence degree; obtaining a second simulation result by running the simulation according to the operating parameter after the second change; and evaluating the second simulation result based on the indexes to obtain and output a second evaluation result.

Patent Agency Ranking