知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.014 seconds)

    Computing numeric representations of words in a high-dimensional space
    3.
    发明授权
    Computing numeric representations of words in a high-dimensional space 有权

    公开(公告)号：US10922488B1

    公开(公告)日：2021-02-16

    申请号：US16363460

    申请日：2019-03-25

    Applicant: Google LLC

    Inventor： Tomas Mikolov ,  Kai Chen ,  Gregory S. Corrado ,  Jeffrey A. Dean

    IPC: G10L15/00 ,  G06F40/279 ,  G10L15/06 ,  G06N20/00 ,  G06F40/30

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.

    Classifying images
    4.
    发明授权
    Classifying images 有权

    公开(公告)号：US10127475B1

    公开(公告)日：2018-11-13

    申请号：US15273572

    申请日：2016-09-22

    Applicant: Google LLC

    Inventor： Gregory S. Corrado ,  Jeffrey A. Dean ,  Samy Bengio ,  Andrea L. Frome ,  Jonathon Shlens

    IPC: G06K9/62

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying images. One of the methods includes obtaining data that associates each of a plurality of object category labels with a respective high-dimensional representation of the object category label, wherein the high-dimensional representation of the object category label is a numeric representation of the object category label in a high-dimensional space; receiving an input image; processing the input image using one or more core layers to generate an alternative representation of the input image; processing the alternative representation of the input image using a transformation layer to determine a high-dimensional representation for the input image; selecting, from the high-dimensional representations associated with the object category labels, a closest high-dimensional representation to the high-dimensional representation for the input image; and selecting the category label associated with the closest high-dimensional representation as a predicted label for the input image.

    Training a model using parameter server shards
    5.
    发明授权
    Training a model using parameter server shards 有权

    公开(公告)号：US10733535B1

    公开(公告)日：2020-08-04

    申请号：US15665236

    申请日：2017-07-31

    Applicant: Google LLC

    Inventor： Gregory S. Corrado ,  Kai Chen ,  Jeffrey A. Dean ,  Samy Bengio ,  Rajat Monga ,  Matthieu Devin

    IPC: G06F15/18 ,  G06N20/00 ,  G06N7/08 ,  G06K9/62 ,  G06N7/00 ,  G06N5/02

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.

    Computing numeric representations of words in a high-dimensional space
    6.
    发明授权
    Computing numeric representations of words in a high-dimensional space 有权

    公开(公告)号：US10241997B1

    公开(公告)日：2019-03-26

    申请号：US15682374

    申请日：2017-08-21

    Applicant: Google LLC

    Inventor： Tomas Mikolov ,  Kai Chen ,  Gregory S. Corrado ,  Jeffrey A. Dean

    IPC: G10L15/00 ,  G06F17/27 ,  G10L15/06

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.

    COMPUTING NUMERIC REPRESENTATIONS OF WORDS IN A HIGH-DIMENSIONAL SPACE
    8.
    发明公开
    COMPUTING NUMERIC REPRESENTATIONS OF WORDS IN A HIGH-DIMENSIONAL SPACE 审中-公开

    公开(公告)号：US20240070392A1

    公开(公告)日：2024-02-29

    申请号：US18503051

    申请日：2023-11-06

    Applicant: Google LLC

    Inventor： Tomas Mikolov ,  Kai Chen ,  Gregory S. Corrado ,  Jeffrey A. Dean

    IPC: G06F40/279 ,  G06F40/30 ,  G06N20/00 ,  G10L15/06

    CPC classification number: G06F40/279 ,  G06F40/30 ,  G06N20/00 ,  G10L15/06

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.

    Computing numeric representations of words in a high-dimensional space
    9.
    发明授权
    Computing numeric representations of words in a high-dimensional space 有权

    公开(公告)号：US11809824B1

    公开(公告)日：2023-11-07

    申请号：US17175550

    申请日：2021-02-12

    Applicant: Google LLC

    Inventor： Tomas Mikolov ,  Kai Chen ,  Gregory S. Corrado ,  Jeffrey A. Dean

    IPC: G06F40/30 ,  G06F40/279 ,  G06N20/00 ,  G10L15/06

    CPC classification number: G06F40/279 ,  G06F40/30 ,  G06N20/00 ,  G10L15/06

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.

    Using embedding functions with a deep network
    10.
    发明授权
    Using embedding functions with a deep network 有权

    公开(公告)号：US11481631B1

    公开(公告)日：2022-10-25

    申请号：US16895855

    申请日：2020-06-08

    Applicant: Google LLC

    Inventor： Gregory S. Corrado ,  Kai Chen ,  Jeffrey A. Dean ,  Gary R. Holt ,  Julian P Grady ,  Sharat Chikkerur ,  David W. Sculley, II

    IPC: G06N3/08 ,  G06N3/04 ,  G06F17/16 ,  G06F7/483

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using embedded function with a deep network. One of the methods includes receiving an input comprising a plurality of features, wherein each of the features is of a different feature type; processing each of the features using a respective embedding function to generate one or more numeric values, wherein each of the embedding functions operates independently of each other embedding function, and wherein each of the embedding functions is used for features of a respective feature type; processing the numeric values using a deep network to generate a first alternative representation of the input, wherein the deep network is a machine learning model composed of a plurality of levels of non-linear operations; and processing the first alternative representation of the input using a logistic regression classifier to predict a label for the input.

Patent Agency Ranking