利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

16 条记录 (耗时 0.018 秒)

    Variational gradient flow
    1.
    发明授权
    Variational gradient flow 有权

    公开(公告)号：US11475304B2

    公开(公告)日：2022-10-18

    申请号：US16872907

    申请日：2020-05-12

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Tomasz Kornuta ,  Ahmet Serkan Ozcan ,  Deepta Rajan ,  Alexis Asseman ,  Chaitanya Shivade

    IPC分类号： G06N3/08 ,  G06N3/04 ,  G16H30/40 ,  G16H50/20

    摘要： According to embodiments of the present disclosure, methods of and computer program products for operating a plurality of classifiers are provided. A plurality of input entities are read, each input entity having an associated target label. The input entities are provided to a first classifier, and a category of each input entity is obtained therefrom. A feature map is determined for each input entity. Each feature map is provided to each of a set of classifiers, and an assigned label is obtained for each feature map from each of the set of classifiers. Each classifier is associated with one of the categories. For each classifier, the assigned label for each feature map is compared to the target labels to determine a plurality of gradients. The plurality of gradients are masked according to each category, yielding a masked set of gradients for each category. Each classifier is trained according its associated masked gradients.

    GUIDED MULTI-SPECTRAL INSPECTION
    2.
    发明申请
    GUIDED MULTI-SPECTRAL INSPECTION 有权

    公开(公告)号：US20220021822A1

    公开(公告)日：2022-01-20

    申请号：US16928371

    申请日：2020-07-14

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Alberto Valdes Garcia ,  Ahmet Serkan Ozcan ,  Vincent Albouy ,  Asaf Tzadok ,  Petar K. Pepeljugoski ,  Jean-Olivier Plouchart

    IPC分类号： H04N5/33 ,  B64C39/02

    摘要： An imaging system is provided. A first imaging system captures initial sensor data in a form of visible domain data. A second imaging system captures subsequent sensor data in a form of second domain data, wherein the initial and subsequent sensor data are of different spectral domains. A controller subsystem detects at least one region of interest in real-time by applying a machine learning technique to the visible domain data, localizes at least one object of interest in the at least one region of interest to generate positional data for the at least one object of interest, and autonomously steers a point of focus of the second imaging system to a region of a scene including the object of interest to capture the second domain data responsive to the positional data.

    DISTRIBUTED MEMORY-AUGMENTED NEURAL NETWORK ARCHITECTURE
    4.
    发明申请
    DISTRIBUTED MEMORY-AUGMENTED NEURAL NETWORK ARCHITECTURE 有权

    公开(公告)号：US20210311874A1

    公开(公告)日：2021-10-07

    申请号：US16838294

    申请日：2020-04-02

    申请人： International Business Machines Corporation

    发明人： Ahmet Serkan Ozcan ,  Tomasz Kornuta ,  Carl Radens ,  Nicolas Antoine

    IPC分类号： G06F12/0817 ,  G06F12/02 ,  G06F16/33 ,  G11C11/4093 ,  G11C11/4076 ,  G06N3/063

    摘要： A method for using a distributed memory device in a memory augmented neural network system includes receiving, by a controller, an input query to access data stored in the distributed memory device, the distributed memory device comprising a plurality of memory banks. The method further includes determining, by the controller, a memory bank selector that identifies a memory bank from the distributed memory device for memory access, wherein the memory bank selector is determined based on a type of workload associated with the input query. The method further includes computing, by the controller and by using content based access, a memory address in the identified memory bank. The method further includes generating, by the controller, an output in response to the input query by accessing the memory address.