中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

23 records (took 0.024 seconds)

    MACHINE LEARNING HYPERPARAMETER TUNING TOOL
    11.
    发明申请
    MACHINE LEARNING HYPERPARAMETER TUNING TOOL 审中-公开

    公开(公告)号：US20190236487A1

    公开(公告)日：2019-08-01

    申请号：US15883686

    申请日：2018-01-30

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Jiapei Huang ,  Houdong Hu ,  Li Huang ,  Xi Chen ,  Linjun Yang

    IPC: G06N99/00

    CPC classification number: G06N20/00 ,  G06F3/04842

    Abstract: A technique for hyperparameter tuning can be performed via a hyperparameter tuning tool. In the technique, computer-readable values for each of one or more machine learning hyperparameters can be received. Multiple computer-readable hyperparameter value sets can be defined using different combinations of the values. In response to a request to start, an overall hyperparameter tuning operation can be performed via the tool, with the overall operation including a tuning job for each of the hyperparameter sets. A computer-readable comparison of the results of the parameter tuning operations can be generated for the hyperparameter sets, with the comparison indicating effectiveness of the hyperparameter sets, as compared to each other, in the tuning jobs.

    FORECASTING JOB APPLICATIONS
    13.
    发明申请
    FORECASTING JOB APPLICATIONS 审中-公开

    公开(公告)号：US20200211041A1

    公开(公告)日：2020-07-02

    申请号：US16232830

    申请日：2018-12-26

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Florian Raudies ,  Sumedha K. Swamy ,  Luthfur R. Chowdhury ,  Xi Chen

    IPC: G06Q30/02 ,  G06N20/00 ,  G06Q10/10

    Abstract: The disclosed embodiments provide a system for forecasting job applications. During operation, the system applies a first machine learning model to features that include a budget for a job to predict a number of impressions of the job. Next, the system applies a second machine learning model to additional features for the job to estimate an application rate for the job. The system then determines a distribution of applications to the job based on the number of impressions and the application rate. Finally, the system outputs one or more values from the distribution of applications to the job as guidance for setting the budget for the job.

    BIDIRECTIONAL SMOOTHING OF ACTIVITY PACING PLANS
    14.
    发明申请
    BIDIRECTIONAL SMOOTHING OF ACTIVITY PACING PLANS 审中-公开

    公开(公告)号：US20200175448A1

    公开(公告)日：2020-06-04

    申请号：US16204574

    申请日：2018-11-29

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Xi Chen ,  Yu Wang

    IPC: G06Q10/06 ,  G06N20/00 ,  G06Q10/10

    Abstract: The disclosed embodiments provide a system for performing bidirectional smoothing of activity pacing plans. During operation, the system obtains historical data comprising a time series of activity with an online system. Next, the system executes a Bayesian model that performs forward filtering of the time series to generate a pacing curve containing smoothed values of the time series over a period. The system then performs a backward smoothing that updates each of the smoothed values based on subsequent values in the time series. Finally, the system adjusts an occurrence of the activity over the period based on the pacing curve.

    OBJECT DETECTION FROM IMAGE CONTENT
    20.
    发明申请
    OBJECT DETECTION FROM IMAGE CONTENT 审中-公开

    公开(公告)号：US20190258895A1

    公开(公告)日：2019-08-22

    申请号：US15900606

    申请日：2018-02-20

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Arun Sacheti ,  Xi Chen ,  Houdong Hu ,  Li Huang ,  Jiapei Huang ,  Meenaz Merchant

    IPC: G06K9/62 ,  G06F17/30

    Abstract: Non-limiting examples of the present disclosure relate to object detection processing of image content that categorically classifies specific objects within image content. Exemplary object detection processing may be utilized to enhance visual search processing including content retrieval and curation, among other technical advantages. An exemplary object detection model is implemented to categorically classify an object. In doing, so an exemplary object detection model may classify objects based on: analysis of specific objects within image content, positioning of the objects within the image content and intent associated with the image content, among other examples. The object detection model generates exemplary categorical classification(s) for specific data objects, which may be propagated to enhance processing efficiency and accuracy during visual search processing. Exemplary categorical classifications may comprise hierarchical classifications of a detected object that can be used to retrieve, curate and surface content that is most contextually relevant to a detected object.

Patent Agency Ranking