中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.016 seconds)

    Off-policy control policy evaluation
    1.
    发明授权
    Off-policy control policy evaluation 有权

    公开(公告)号：US11477243B2

    公开(公告)日：2022-10-18

    申请号：US16827596

    申请日：2020-03-23

    Applicant: Google LLC

    Inventor： Kanury Kanishka Rao ,  Konstantinos Bousmalis ,  Christopher K. Harris ,  Alexander Irpan ,  Sergey Vladimir Levine ,  Julian Ibarz

    IPC: G06N20/20 ,  H04L9/40 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for off-policy evaluation of a control policy. One of the methods includes obtaining policy data specifying a control policy for controlling a source agent interacting with a source environment to perform a particular task; obtaining a validation data set generated from interactions of a target agent in a target environment; determining a performance estimate that represents an estimate of a performance of the control policy in controlling the target agent to perform the particular task in the target environment; and determining, based on the performance estimate, whether to deploy the control policy for controlling the target agent to perform the particular task in the target environment.

    Domain separation neural networks
    3.
    发明授权
    Domain separation neural networks 有权

    公开(公告)号：US10970589B2

    公开(公告)日：2021-04-06

    申请号：US16321189

    申请日：2016-07-28

    Applicant: GOOGLE LLC

    Inventor： Konstantinos Bousmalis ,  Nathan Silberman ,  Dilip Krishnan ,  George Trigeorgis ,  Dumitru Erhan

    IPC: G06K9/46 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06T7/73

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.

    SEMANTICALLY-CONSISTENT IMAGE STYLE TRANSFER
    4.
    发明申请
    SEMANTICALLY-CONSISTENT IMAGE STYLE TRANSFER 审中-公开

    公开(公告)号：US20200342643A1

    公开(公告)日：2020-10-29

    申请号：US16759689

    申请日：2018-10-29

    Applicant: GOOGLE LLC

    Inventor： Stephan Gouws ,  Frederick Bertsch ,  Konstantinos Bousmalis ,  Amelie Royer ,  Kevin Patrick Murphy

    IPC: G06T11/60 ,  G06F16/55 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for semantically-consistent image style transfer. One of the methods includes: receiving an input source domain image; processing the source domain image using one or more source domain low-level encoder neural network layers to generate a low-level representation; processing the low-level representation using one more high-level encoder neural network layers to generate an embedding of the input source domain image; processing the embedding using one or more high-level decoder neural network layers to generate a high-level feature representation of features of the input source domain image; and processing the high-level feature representation of the features of the input source domain image using one or more target domain low-level decoder neural network layers to generate an output target domain image that is from the target domain but that has similar semantics to the input source domain image.

    TRANSFORMING SOURCE DOMAIN IMAGES INTO TARGET DOMAIN IMAGES
    5.
    发明申请
    TRANSFORMING SOURCE DOMAIN IMAGES INTO TARGET DOMAIN IMAGES 审中-公开

    公开(公告)号：US20190304065A1

    公开(公告)日：2019-10-03

    申请号：US16442365

    申请日：2019-06-14

    Applicant: Google LLC

    Inventor： Konstantinos Bousmalis ,  Nathan Silberman ,  David Martin Dohan ,  Dumitru Erhan ,  Dilip Krishnan

    IPC: G06T3/40 ,  G06N3/08 ,  G06N20/10

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the systems includes a domain transformation neural network implemented by one or more computers, wherein the domain transformation neural network is configured to: receive an input image from a source domain; and process a network input comprising the input image from the source domain to generate a transformed image that is a transformation of the input image from the source domain to a target domain that is different from the source domain.

    Semantically-consistent image style transfer
    6.
    发明授权
    Semantically-consistent image style transfer 有权

    公开(公告)号：US11380034B2

    公开(公告)日：2022-07-05

    申请号：US16759689

    申请日：2018-10-29

    Applicant: GOOGLE LLC

    Inventor： Stephan Gouws ,  Frederick Bertsch ,  Konstantinos Bousmalis ,  Amelie Royer ,  Kevin Patrick Murphy

    IPC: G06T11/60 ,  G06F16/55 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for semantically-consistent image style transfer. One of the methods includes: receiving an input source domain image; processing the source domain image using one or more source domain low-level encoder neural network layers to generate a low-level representation; processing the low-level representation using one more high-level encoder neural network layers to generate an embedding of the input source domain image; processing the embedding using one or more high-level decoder neural network layers to generate a high-level feature representation of features of the input source domain image; and processing the high-level feature representation of the features of the input source domain image using one or more target domain low-level decoder neural network layers to generate an output target domain image that is from the target domain but that has similar semantics to the input source domain image.

    Domain separation neural networks
    7.
    发明授权
    Domain separation neural networks 有权

    公开(公告)号：US11361531B2

    公开(公告)日：2022-06-14

    申请号：US17222782

    申请日：2021-04-05

    Applicant: Google LLC

    Inventor： Konstantinos Bousmalis ,  Nathan Silberman ,  Dilip Krishnan ,  George Trigeorgis ,  Dumitru Erhan

    IPC: G06K9/46 ,  G06V10/44 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06T7/73

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.

    OFF-POLICY CONTROL POLICY EVALUATION
    8.
    发明申请
    OFF-POLICY CONTROL POLICY EVALUATION 审中-公开

    公开(公告)号：US20200304545A1

    公开(公告)日：2020-09-24

    申请号：US16827596

    申请日：2020-03-23

    Applicant: Google LLC

    Inventor： Kanury Kanishka Rao ,  Konstantinos Bousmalis ,  Christopher K. Harris ,  Alexander Irpan ,  Sergey Vladimir Levine ,  Julian Ibarz

    IPC: H04L29/06 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for off-policy evaluation of a control policy. One of the methods includes obtaining policy data specifying a control policy for controlling a source agent interacting with a source environment to perform a particular task; obtaining a validation data set generated from interactions of a target agent in a target environment; determining a performance estimate that represents an estimate of a performance of the control policy in controlling the target agent to perform the particular task in the target environment; and determining, based on the performance estimate, whether to deploy the control policy for controlling the target agent to perform the particular task in the target environment.

Patent Agency Ranking