中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.014 seconds)

    SECURE EXECUTION OF A MACHINE LEARNING NETWORK
    1.
    发明公开
    SECURE EXECUTION OF A MACHINE LEARNING NETWORK 审中-公开

    公开(公告)号：US20230334146A1

    公开(公告)日：2023-10-19

    申请号：US17927854

    申请日：2021-05-10

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Yunxin LIU ,  Jiahui HOU

    IPC: G06F21/53

    CPC classification number: G06F21/53

    Abstract: According to implementations of the subject matter described herein, there is provided a solution for secure execution of a machine learning network. An operation of a first network layer of a machine learning network is executed in an uTEE of a computing device based on an input of the first network layer and a first set of modified parameter values, to obtain a first error intermediate In output. The modified parameter values are determined by modifying at least one subset of parameter values of the first network layer with first secret data. A first corrected intermediate output is determined in a TEE of the computing device by modifying the first error intermediate output at least based on the input and first secret data. A network output is determined based on the first corrected intermediate output. In this way, it is possible to protect the confidentiality of the machine learning network.

    ADAPTIVE OBJECT DETECTION
    2.
    发明公开
    ADAPTIVE OBJECT DETECTION 审中-公开

    公开(公告)号：US20240233311A1

    公开(公告)日：2024-07-11

    申请号：US18562784

    申请日：2021-06-30

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Shiqi JIANG ,  Yuanchun LI ,  Yuanchao SHU ,  Yunxin LIU

    IPC: G06V10/25 ,  G06T3/40 ,  G06T7/11 ,  G06T7/62

    CPC classification number: G06V10/25 ,  G06T3/40 ,  G06T7/11 ,  G06T7/62 ,  G06V2201/07

    Abstract: Implementations of the present disclosure provide a solution for object detection. In this solution, object distribution information and performance metrics are obtained. The object distribution information indicates a size distribution of detected objects in a set of historical images captured by a camera. The performance metric indicates corresponding performance levels of a set of predetermined object detection models. At least one detection plan is further generated based on the object distribution information and the performance metric. The at least one detection plan indicates which of the set of predetermined object detection models is to be applied to each of at least one sub-image in a target image to be captured by the camera. Additionally, the at least one detection plan is provided for object detection on the target image. In this way, a balance between the detection latency and the detection accuracy may be improved.

    EXECUTION OF DEEP-LEARNING MODEL
    3.
    发明申请
    EXECUTION OF DEEP-LEARNING MODEL 有权

    公开(公告)号：US20220215251A1

    公开(公告)日：2022-07-07

    申请号：US17606856

    申请日：2020-04-27

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Yunxin LIU ,  Lintao ZHANG

    IPC: G06N3/08 ,  G06N3/04 ,  G06F17/16 ,  G06F21/53

    Abstract: In accordance with implementations of the subject matter described herein, there is provided a solution for execution of a deep learning model. In the solution, partitioned convolutions are executed based on an input and a set of parameter values of the convolutional layer sequentially in a trusted execution environment (TEE) of a computing device. The execution of a given one of partitioned convolutions comprises: storing, into a protected memory area in the TEE, an input portion of the input to be processed by a subset of parameter values for the given partitioned convolution; determining a result of the given partitioned convolution through a single matrix multiplication operation; and removing the input portion. By combining results of the partitioned convolutions, a result of the convolution is determined. Therefore, the solution can accelerate the model execution speed and improve the storage efficiency in a highly safe TEE with limited memory resources.

    SPARSE CONVOLUTIONAL NEURAL NETWORK
    4.
    发明申请
    SPARSE CONVOLUTIONAL NEURAL NETWORK 有权

    公开(公告)号：US20220245433A1

    公开(公告)日：2022-08-04

    申请号：US17615077

    申请日：2020-04-29

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Chen Zhang ,  Yunxin LIU

    IPC: G06N3/04 ,  G06N3/10 ,  G06F17/15 ,  G06F5/01

    Abstract: Various implementations of the subject matter as described herein relate to a sparse convolutional neural network. In some implementations, a computer-implemented method comprises: quantizing an input feature map to obtain a quantized input feature map; determining, based on the quantized input feature map, a sparsity mask for an output feature map through a quantized version of a convolutional neural network, the sparsity mask indicating positions of non-zero entries in the output feature map; and determining, based on the input feature map, the non-zero entries indicated by the sparsity mask in the output feature map through the convolutional neural network.

    POWER SAVING WI-FI TETHERING
    7.
    发明申请
    POWER SAVING WI-FI TETHERING 审中-公开
    省电WI-FI TETHERING

    公开(公告)号：US20160100359A1

    公开(公告)日：2016-04-07

    申请号：US14967012

    申请日：2015-12-11

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Yunxin LIU ,  Guobin SHEN ,  Yongguang ZHANG ,  Hao HAN

    IPC: H04W52/02

    CPC classification number: H04W52/0206 ,  H04W52/0216 ,  Y02D70/124 ,  Y02D70/126 ,  Y02D70/142 ,  Y02D70/26

    Abstract: The techniques discussed herein reduce the power consumption of a Wi-Fi tethering device by switching the Wi-Fi functionality of the Wi-Fi tethering device from a normal operational mode to a sleep mode during idle intervals. The techniques implement a sleep protocol where a Wi-Fi tethering device and the Wi-Fi client device coordinate and establish a sleep schedule. Moreover, the techniques describe a sleep interval adaptation algorithm to establish sleep duration intervals based on data packet exchange patterns associated with different applications executing on the Wi-Fi client device and/or different operations being performed by the Wi-Fi client device.

    Abstract translation: 本文讨论的技术通过在空闲间隔期间将Wi-Fi束缚设备的Wi-Fi功能从正常操作模式切换到睡眠模式来降低Wi-Fi束缚设备的功耗。 该技术实现睡眠协议，其中Wi-Fi网络共享设备和Wi-Fi客户端设备协调并建立睡眠时间表。 此外，技术描述了基于与在Wi-Fi客户端设备上执行的不同应用相关联的数据分组交换模式和/或由Wi-Fi客户端设备执行的不同操作来建立睡眠持续时间间隔的睡眠间隔自适应算法。

    WIRELESS PROGRAMMABLE MEDIA PROCESSING SYSTEM
    8.
    发明申请
    WIRELESS PROGRAMMABLE MEDIA PROCESSING SYSTEM 有权

    公开(公告)号：US20230077904A1

    公开(公告)日：2023-03-16

    申请号：US17986683

    申请日：2022-11-14

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Yunxin LIU ,  Jiansong ZHANG ,  Lintao ZHANG ,  Thomas MOSCIBRODA

    IPC: G09G5/36

    Abstract: Embodiments of the subject matter described herein relate to a wireless programmable media processing system. In the media processing system, a processing unit in a computing device generates a frame to be displayed based on a graphics content for an application running on the computing device. The frame to be displayed is then divided into a plurality of block groups which are compressed. The plurality of compressed block groups are sent to a graphics display device over a wireless link. In this manner, both the generation and the compression of the frame to be displayed may be completed at the same processing unit in the computing device, which avoids data copying and simplifies processing operations. Thereby, the data processing speed and efficiency is improved significantly.

Patent Agency Ranking