中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.015 seconds)

    Image processing neural networks with separable convolutional layers
    2.
    发明授权
    Image processing neural networks with separable convolutional layers 有权

    公开(公告)号：US11593614B2

    公开(公告)日：2023-02-28

    申请号：US16338963

    申请日：2017-10-06

    Applicant: Google LLC

    Inventor： Francois Chollet ,  Andrew Gerald Howard

    IPC: G06N3/04 ,  G06N3/08 ,  G06K9/62 ,  G06V40/16 ,  G06V10/44

    Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

    DEPTHWISE SEPARABLE CONVOLUTIONS FOR NEURAL MACHINE TRANSLATION
    3.
    发明申请
    DEPTHWISE SEPARABLE CONVOLUTIONS FOR NEURAL MACHINE TRANSLATION 审中-公开

    公开(公告)号：US20200089772A1

    公开(公告)日：2020-03-19

    申请号：US16688958

    申请日：2019-11-19

    Applicant: Google LLC

    Inventor： Aidan Nicholas Gomez ,  Lukasz Mieczyslaw Kaiser ,  Francois Chollet

    IPC: G06F17/28 ,  G06N3/08 ,  G06N3/04 ,  G06F17/27

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS
    4.
    发明公开
    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS 审中-公开

    公开(公告)号：US20230237314A1

    公开(公告)日：2023-07-27

    申请号：US18114333

    申请日：2023-02-27

    Applicant: Google LLC

    Inventor： Francois Chollet ,  Andrew Gerald Howard

    IPC: G06N3/0464 ,  G06V10/82

    CPC classification number: G06N3/0464 ,  G06V10/82

    Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS
    5.
    发明申请
    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS 有权

    公开(公告)号：US20210027140A1

    公开(公告)日：2021-01-28

    申请号：US16338963

    申请日：2017-10-06

    Applicant: Google LLC

    Inventor： Francois Chollet ,  Andrew Gerald Howard

    IPC: G06N3/04 ,  G06N3/08

    Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

    Depthwise separable convolutions for neural machine translation
    6.
    发明授权
    Depthwise separable convolutions for neural machine translation 有权

    公开(公告)号：US10853590B2

    公开(公告)日：2020-12-01

    申请号：US16688958

    申请日：2019-11-19

    Applicant: Google LLC

    Inventor： Aidan Nicholas Gomez ,  Lukasz Mieczyslaw Kaiser ,  Francois Chollet

    IPC: G10L25/30 ,  G06F40/58 ,  G06F40/263 ,  G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

    DEPTHWISE SEPARABLE CONVOLUTIONS FOR NEURAL MACHINE TRANSLATION
    9.
    发明申请
    DEPTHWISE SEPARABLE CONVOLUTIONS FOR NEURAL MACHINE TRANSLATION 有权

    公开(公告)号：US20210073481A1

    公开(公告)日：2021-03-11

    申请号：US17100169

    申请日：2020-11-20

    Applicant: Google LLC

    Inventor： Aidan Nicholas Gomez ,  Lukasz Mieczyslaw Kaiser ,  Francois Chollet

    IPC: G06F40/58 ,  G06F40/263 ,  G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

    CLASSIFYING IMAGES USING MACHINE LEARNING MODELS
    10.
    发明申请
    CLASSIFYING IMAGES USING MACHINE LEARNING MODELS 审中-公开

    公开(公告)号：US20190266487A1

    公开(公告)日：2019-08-29

    申请号：US16317763

    申请日：2017-07-14

    Applicant: GOOGLE LLC

    Inventor： Francois Chollet

    IPC: G06N3/08 ,  G06N20/00 ,  G06K9/62 ,  G06K9/66

    Abstract: Systems and methods for classifying an image using a machine learning model. One of the methods includes obtaining training data for training the machine learning model, wherein the machine learning model is configured to process input images to generate, for each input image, a predicted point in an embedding space; determining, from label data for training images in the training data, a respective numeric embedding of each of the object categories, wherein a distance in the embedding space between the numeric embeddings of any two object categories reflects a degree of visual co-occurrence of the two object categories; and training the machine learning model on the training data. The systems described in this specification can effectively perform multi-label, massively multi-category image classification, where the number of classes is large (many thousands or tens of thousands) and where each image typically belongs to multiple categories that should all be properly identified.

Patent Agency Ranking