中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.011 seconds)

    Training neural networks represented as computational graphs
    3.
    发明授权
    Training neural networks represented as computational graphs 有权

    公开(公告)号：US10970628B2

    公开(公告)日：2021-04-06

    申请号：US15347618

    申请日：2016-11-09

    Applicant: Google LLC

    Inventor： Yuan Yu ,  Manjunath Kudlur Venkatakrishna

    IPC: G06N3/08 ,  G06F9/50 ,  G06N3/04

    Abstract: Systems and Methods for training a neural network represented as a computational graph are disclosed. An example method begins with obtaining data representing a computational graph. The computational graph is then augmented to generate a training computational graph for training the neural network using a machine learning training algorithm that includes computing a gradient of an objective function with respect to each of the parameters of the neural network. Augmenting the computational graph includes inserting a plurality of gradient nodes and training edges into the computational graph to generate a backward path through the computational graph that represents operations for computing the gradients of the objective function with respect to the parameters of the neural network. The neural network is trained using the machine learning training algorithm by executing the training computational graph.

    Stylizing input images
    4.
    发明授权
    Stylizing input images 有权

    公开(公告)号：US10535164B2

    公开(公告)日：2020-01-14

    申请号：US16380010

    申请日：2019-04-10

    Applicant: Google LLC

    Inventor： Jonathon Shlens ,  Vincent Dumoulin ,  Manjunath Kudlur Venkatakrishna

    IPC: G06N3/08 ,  G06N3/04 ,  G06T11/00 ,  G06K9/62

    Abstract: A method for applying a style to an input image to generate a stylized image. The method includes maintaining data specifying respective parameter values for each image style in a set of image styles, receiving an input including an input image and data identifying an input style to be applied to the input image to generate a stylized image that is in the input style, determining, from the maintained data, parameter values for the input style, and generating the stylized image by processing the input image using a style transfer neural network that is configured to process the input image to generate the stylized image.

    TRAINING NEURAL NETWORKS REPRESENTED AS COMPUTATIONAL GRAPHS
    5.
    发明申请
    TRAINING NEURAL NETWORKS REPRESENTED AS COMPUTATIONAL GRAPHS 有权

    公开(公告)号：US20210295161A1

    公开(公告)日：2021-09-23

    申请号：US17221305

    申请日：2021-04-02

    Applicant: Google LLC

    Inventor： Yuan Yu ,  Manjunath Kudlur Venkatakrishna

    IPC: G06N3/08 ,  G06F9/50 ,  G06N3/04

    Abstract: Systems and Methods for training a neural network represented as a computational graph are disclosed. An example method begins with obtaining data representing a computational graph. The computational graph is then augmented to generate a training computational graph for training the neural network using a machine learning training algorithm that includes computing a gradient of an objective function with respect to each of the parameters of the neural network. Augmenting the computational graph includes inserting a plurality of gradient nodes and training edges into the computational graph to generate a backward path through the computational graph that represents operations for computing the gradients of the objective function with respect to the parameters of the neural network. The neural network is trained using the machine learning training algorithm by executing the training computational graph.

    STYLIZING INPUT IMAGES
    6.
    发明申请
    STYLIZING INPUT IMAGES 审中-公开

    公开(公告)号：US20190236814A1

    公开(公告)日：2019-08-01

    申请号：US16380010

    申请日：2019-04-10

    Applicant: Google LLC

    Inventor： Jonathon Shlens ,  Vincent Dumoulin ,  Manjunath Kudlur Venkatakrishna

    IPC: G06T11/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

    CPC classification number: G06T11/001 ,  G06K9/6253 ,  G06K9/6256 ,  G06N3/04 ,  G06N3/08 ,  G06T11/00

    Abstract: A method for applying a style to an input image to generate a stylized image. The method includes maintaining data specifying respective parameter values for each image style in a set of image styles, receiving an input including an input image and data identifying an input style to be applied to the input image to generate a stylized image that is in the input style, determining, from the maintained data, parameter values for the input style, and generating the stylized image by processing the input image using a style transfer neural network that is configured to process the input image to generate the stylized image.

    STYLIZING INPUT IMAGES
    7.
    发明申请
    STYLIZING INPUT IMAGES 审中-公开

    公开(公告)号：US20200082578A1

    公开(公告)日：2020-03-12

    申请号：US16681391

    申请日：2019-11-12

    Applicant: Google LLC

    Inventor： Jonathon Shlens ,  Vincent Dumoulin ,  Manjunath Kudlur Venkatakrishna

    IPC: G06T11/00 ,  G06N3/04 ,  G06K9/62 ,  G06N3/08

    Abstract: A method for applying a style to an input image to generate a stylized image. The method includes maintaining data specifying respective parameter values for each image style in a set of image styles, receiving an input including an input image and data identifying an input style to be applied to the input image to generate a stylized image that is in the input style, determining, from the maintained data, parameter values for the input style, and generating the stylized image by processing the input image using a style transfer neural network that is configured to process the input image to generate the stylized image.

Patent Agency Ranking