中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.013 seconds)

    Regularization relaxation scheme
    2.
    发明授权
    Regularization relaxation scheme 有权

    公开(公告)号：US10438129B1

    公开(公告)日：2019-10-08

    申请号：US14586043

    申请日：2014-12-30

    Applicant: Google LLC

    Inventor： Yoram Singer ,  Tal Shaked ,  Tushar Deepak Chandra ,  Tze Way Eugene Ie

    IPC: G06N20/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training machine learning systems. One of the methods includes receiving a plurality of training examples; and training a machine learning system on each of the plurality of training examples to determine trained values for weights of a machine learning model, wherein training the machine learning system comprises: assigning an initial value for a regularization penalty for a particular weight for a particular feature; and adjusting the initial value for the regularization penalty for the particular weight for the particular feature during the training of the machine learning system.

    Searchable index
    3.
    发明授权
    Searchable index 有权

    公开(公告)号：US10255319B2

    公开(公告)日：2019-04-09

    申请号：US14268049

    申请日：2014-05-02

    Applicant: Google LLC

    Inventor： Jeremiah Harmsen ,  Tushar Deepak Chandra ,  Marcus Fontoura

    IPC: G06F17/30 ,  G06N99/00 ,  G06N5/02

    Abstract: Systems and techniques are disclosed for generating entries for a searchable index based on rules generated by one or more machine-learned models. The index entries can include one or more tokens correlated with an outcome and an outcome probability. A subset of tokens can be identified based on the characteristics of an event. The index may be searched for outcomes and their respective probabilities that correspond to tokens that are similar to or match the subset of tokens based on the event.

    Regularization relaxation scheme
    4.
    发明授权
    Regularization relaxation scheme 有权

    公开(公告)号：US11663520B1

    公开(公告)日：2023-05-30

    申请号：US16551610

    申请日：2019-08-26

    Applicant: Google LLC

    Inventor： Yoram Singer ,  Tal Shaked ,  Tushar Deepak Chandra ,  Tze Way Eugene Ie

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training machine learning systems. One of the methods includes receiving a plurality of training examples; and training a machine learning system on each of the plurality of training examples to determine trained values for weights of a machine learning model, wherein training the machine learning system comprises: assigning an initial value for a regularization penalty for a particular weight for a particular feature; and adjusting the initial value for the regularization penalty for the particular weight for the particular feature during the training of the machine learning system.

    Efficient locking of large data collections
    5.
    发明授权
    Efficient locking of large data collections 有权

    公开(公告)号：US10509772B1

    公开(公告)日：2019-12-17

    申请号：US15393071

    申请日：2016-12-28

    Applicant: Google LLC

    Inventor： Tushar Deepak Chandra ,  Tal Shaked ,  Yoram Singer ,  Tze Way Eugene le ,  Joshua Redstone

    IPC: G06F7/00 ,  G06F16/176 ,  G06F16/23

    Abstract: The present disclosure provides systems and techniques for efficient locking of datasets in a database when updates to a dataset may be delayed. A method may include accumulating a plurality of updates to a first set of one or more values associated with one or more features. The first set of one or more values may be stored within a first database column. Next, it may be determined that a first database column update aggregation rule is satisfied. A lock assigned to at least a portion of at least a first database column may be acquired. Accordingly, one or more values in the first set within the first database column may be updated based on the plurality of updates. In an implementation, the first set of one or more values may be associated with the first lock.

    Wide and deep machine learning models
    6.
    发明授权
    Wide and deep machine learning models 有权

    公开(公告)号：US10762422B2

    公开(公告)日：2020-09-01

    申请号：US15394668

    申请日：2016-12-29

    Applicant: Google LLC

    Inventor： Tal Shaked ,  Rohan Anil ,  Hrishikesh Balkrishna Aradhye ,  Mustafa Ispir ,  Glen Anderson ,  Wei Chai ,  Mehmet Levent Koc ,  Jeremiah Harmsen ,  Xiaobing Liu ,  Gregory Sean Corrado ,  Tushar Deepak Chandra ,  Heng-Tze Cheng

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A system includes one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the computers to implement a combined machine learning model for processing an input including multiple features to generate a predicted output for the machine learning input. The combined model includes: a deep machine learning model configured to process the features to generate a deep model output; a wide machine learning model configured to process the features to generate a wide model output; and a combining layer configured to process the deep model output generated by the deep machine learning model and the wide model output generated by the wide machine learning model to generate the predicted output, in which the deep model and the wide model have been trained jointly on training data to generate the deep model output and the wide model output.

    Searchable index
    8.
    发明授权
    Searchable index 有权

    公开(公告)号：US12254007B2

    公开(公告)日：2025-03-18

    申请号：US18482756

    申请日：2023-10-06

    Applicant: Google LLC

    Inventor： Jeremiah Harmsen ,  Tushar Deepak Chandra ,  Marcus Fontoura

    IPC: G06F16/24 ,  G06F16/22 ,  G06F16/245 ,  G06F16/31 ,  G06N5/025 ,  G06N20/00

    Abstract: Systems and techniques are disclosed for generating entries for a searchable index based on rules generated by one or more machine-learned models. The index entries can include one or more tokens correlated with an outcome and an outcome probability. A subset of tokens can be identified based on the characteristics of an event. The index may be searched for outcomes and their respective probabilities that correspond to tokens that are similar to or match the subset of tokens based on the event.

    Searchable index
    10.
    发明授权
    Searchable index 有权

    公开(公告)号：US10853360B2

    公开(公告)日：2020-12-01

    申请号：US16366260

    申请日：2019-03-27

    Applicant: Google LLC

    Inventor： Jeremiah Harmsen ,  Tushar Deepak Chandra ,  Marcus Fontoura

    IPC: G06F16/31 ,  G06F16/245 ,  G06N20/00 ,  G06F16/22 ,  G06N5/02

    Abstract: Systems and techniques are disclosed for generating entries for a searchable index based on rules generated by one or more machine-learned models. The index entries can include one or more tokens correlated with an outcome and an outcome probability. A subset of tokens can be identified based on the characteristics of an event. The index may be searched for outcomes and their respective probabilities that correspond to tokens that are similar to or match the subset of tokens based on the event.

Patent Agency Ranking