利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

34 条记录 (耗时 0.038 秒)

    Systems and methods for distributed communications and processing
    1.
    发明授权
    Systems and methods for distributed communications and processing 有权
    用于分布式通信和处理的系统和方法

    公开(公告)号：US09596664B2

    公开(公告)日：2017-03-14

    申请号：US14038894

    申请日：2013-09-27

    申请人： Maynard C. Falconer ,  Omesh Tickoo ,  Shilpa Talwar ,  Vallabhajosyula S. Somayazulu ,  Xingang Guo

    发明人： Maynard C. Falconer ,  Omesh Tickoo ,  Shilpa Talwar ,  Vallabhajosyula S. Somayazulu ,  Xingang Guo

    IPC分类号： H04W4/00 ,  H04W52/46 ,  H04W40/24

    CPC分类号： H04W52/46 ,  H04W40/246

    摘要： Systems and methods to provide distributed wireless communications from a plurality of wireless network devices are disclosed. The plurality of wireless network devices may be configured to provide direction communications with one or more user devices. This may be performed by adjusting one or more radio parameters associated with the plurality of wireless network devices. The plurality of wireless network devices may cooperate with each other to provide network connectivity for the one or more user devices with relatively high fidelity, relatively high bandwidth, and relatively low power consumption. The plurality of wireless network devices may further provide distributed processing capability to perform tasks for user devices that may provide task requests.

    摘要翻译： 公开了从多个无线网络设备提供分布式无线通信的系统和方法。 多个无线网络设备可以被配置为提供与一个或多个用户设备的方向通信。 这可以通过调整与多个无线网络设备相关联的一个或多个无线电参数来执行。 多个无线网络设备可以彼此协作以为具有相对高保真度，相对高带宽和相对低功耗的一个或多个用户设备提供网络连接。 多个无线网络设备可以进一步提供分布式处理能力以对可能提供任务请求的用户设备执行任务。

    COMPRESSION FOR SPLIT NEURAL NETWORK COMPUTING TO ACCOMMODATE VARYING BITRATE
    5.
    发明申请
    COMPRESSION FOR SPLIT NEURAL NETWORK COMPUTING TO ACCOMMODATE VARYING BITRATE 有权

    公开(公告)号：US20220327359A1

    公开(公告)日：2022-10-13

    申请号：US17853407

    申请日：2022-06-29

    申请人： Nilesh A. Ahuja ,  Parual Datta ,  Vallabhajosyula S. Somayazulu ,  Omesh Tickoo

    发明人： Nilesh A. Ahuja ,  Parual Datta ,  Vallabhajosyula S. Somayazulu ,  Omesh Tickoo

    IPC分类号： G06N3/04

    摘要： Various systems and methods for providing variable bitrate compression for split deep neural network (DNN) computing are described herein. A system may be configured to manage a split DNN, the split DNN configured to operate on a compute system and a second system over a communication network. The system may access a performance metric; determine, based on the performance metric, a split point of the split DNN, the split point defining a head portion of the split DNN and a tail portion of the split DNN; determine, based on the performance metric, a bottleneck layer configuration for a bottleneck layer at the split point, the bottleneck layer including a bottleneck encoder and a bottleneck decoder; execute the head portion of the DNN and the bottleneck encoder on the compute system; and recurrently access an updated performance metric and determine a revised split point or a revised bottleneck layer configuration based on the updated performance metric.