中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.017 seconds)

    SAMPLING LATENT VARIABLES TO GENERATE MULTIPLE SEGMENTATIONS OF AN IMAGE
    1.
    发明申请
    SAMPLING LATENT VARIABLES TO GENERATE MULTIPLE SEGMENTATIONS OF AN IMAGE 审中-公开

    公开(公告)号：US20200372654A1

    公开(公告)日：2020-11-26

    申请号：US16881775

    申请日：2020-05-22

    Applicant: DeepMind Technologies Limited

    Inventor： Simon Kohl ,  Bernardino Romera-Paredes ,  Danilo Jimenez Rezende ,  Seyed Mohammadali Eslami ,  Pushmeet Kohli ,  Andrew Zisserman ,  Olaf Ronneberger

    IPC: G06T7/10 ,  G06T7/00 ,  A61B5/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a plurality of possible segmentations of an image. In one aspect, a method comprises: receiving a request to generate a plurality of possible segmentations of an image; sampling a plurality of latent variables from a latent space, wherein each latent variable is sampled from the latent space in accordance with a respective probability distribution over the latent space that is determined based on the image; generating a plurality of possible segmentations of the image, comprising, for each latent variable, processing the image and the latent variable using a segmentation neural network having a plurality of segmentation neural network parameters to generate the possible segmentation of the image; and providing the plurality of possible segmentations of the image in response to the request.

    Action selection using interaction history graphs
    3.
    发明授权
    Action selection using interaction history graphs 有权

    公开(公告)号：US11636347B2

    公开(公告)日：2023-04-25

    申请号：US16749252

    申请日：2020-01-22

    Applicant: DeepMind Technologies Limited

    Inventor： Hanjun Dai ,  Yujia Li ,  Chenglong Wang ,  Rishabh Singh ,  Po-Sen Huang ,  Pushmeet Kohli

    IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06N3/088 ,  G06N3/049

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining a graph of nodes and edges that represents an interaction history of the agent with the environment; generating an encoded representation of the graph representing the interaction history of the agent with the environment; processing an input based on the encoded representation of the graph using an action selection neural network, in accordance with current values of action selection neural network parameters, to generate an action selection output; and selecting an action from a plurality of possible actions to be performed by the agent using the action selection output generated by the action selection neural network.

    Deep neural network system for similarity-based graph representations
    6.
    发明授权
    Deep neural network system for similarity-based graph representations 有权

    公开(公告)号：US11537719B2

    公开(公告)日：2022-12-27

    申请号：US16416070

    申请日：2019-05-17

    Applicant: DeepMind Technologies Limited

    Inventor： Yujia Li ,  Chenjie Gu ,  Thomas Dullien ,  Oriol Vinyals ,  Pushmeet Kohli

    IPC: G08B23/00 ,  G06F12/16 ,  G06F12/14 ,  G06F11/00 ,  G06F21/57 ,  G06N3/04 ,  G06F17/16 ,  G06F16/901 ,  G06K9/62

    Abstract: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.

    Sampling latent variables to generate multiple segmentations of an image
    7.
    发明授权
    Sampling latent variables to generate multiple segmentations of an image 有权

    公开(公告)号：US11430123B2

    公开(公告)日：2022-08-30

    申请号：US16881775

    申请日：2020-05-22

    Applicant: DeepMind Technologies Limited

    Inventor： Simon Kohl ,  Bernardino Romera-Paredes ,  Danilo Jimenez Rezende ,  Seyed Mohammadali Eslami ,  Pushmeet Kohli ,  Andrew Zisserman ,  Olaf Ronneberger

    IPC: G06T7/10 ,  A61B5/00 ,  G06T7/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a plurality of possible segmentations of an image. In one aspect, a method comprises: receiving a request to generate a plurality of possible segmentations of an image; sampling a plurality of latent variables from a latent space, wherein each latent variable is sampled from the latent space in accordance with a respective probability distribution over the latent space that is determined based on the image; generating a plurality of possible segmentations of the image, comprising, for each latent variable, processing the image and the latent variable using a segmentation neural network having a plurality of segmentation neural network parameters to generate the possible segmentation of the image; and providing the plurality of possible segmentations of the image in response to the request.

    ACTION SELECTION USING INTERACTION HISTORY GRAPHS
    8.
    发明申请
    ACTION SELECTION USING INTERACTION HISTORY GRAPHS 审中-公开

    公开(公告)号：US20200234145A1

    公开(公告)日：2020-07-23

    申请号：US16749252

    申请日：2020-01-22

    Applicant: DeepMind Technologies Limited

    Inventor： Hanjun Dai ,  Yujia Li ,  Chenglong Wang ,  Rishabh Singh ,  Po-Sen Huang ,  Pushmeet Kohli

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

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining a graph of nodes and edges that represents an interaction history of the agent with the environment; generating an encoded representation of the graph representing the interaction history of the agent with the environment; processing an input based on the encoded representation of the graph using an action selection neural network, in accordance with current values of action selection neural network parameters, to generate an action selection output; and selecting an action from a plurality of possible actions to be performed by the agent using the action selection output generated by the action selection neural network.

    DEEP NEURAL NETWORK SYSTEM FOR SIMILARITY-BASED GRAPH REPRESENTATIONS
    9.
    发明申请
    DEEP NEURAL NETWORK SYSTEM FOR SIMILARITY-BASED GRAPH REPRESENTATIONS 有权

    公开(公告)号：US20230134742A1

    公开(公告)日：2023-05-04

    申请号：US18087704

    申请日：2022-12-22

    Applicant: DeepMind Technologies Limited

    Inventor： Yujia Li ,  Chenjie Gu ,  Thomas Dullien ,  Oriol Vinyals ,  Pushmeet Kohli

    IPC: G06F21/56 ,  G06F21/57 ,  G06N3/04 ,  G06F17/16 ,  G06F16/901 ,  G06F18/22 ,  G06V30/196 ,  G06V10/82 ,  G06V10/426

    Abstract: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.

    DEEP NEURAL NETWORK SYSTEM FOR SIMILARITY-BASED GRAPH REPRESENTATIONS
    10.
    发明申请
    DEEP NEURAL NETWORK SYSTEM FOR SIMILARITY-BASED GRAPH REPRESENTATIONS 审中-公开

    公开(公告)号：US20190354689A1

    公开(公告)日：2019-11-21

    申请号：US16416070

    申请日：2019-05-17

    Applicant: DeepMind Technologies Limited

    Inventor： Yujia Li ,  Chenjie Gu ,  Thomas Dullien ,  Oriol Vinyals ,  Pushmeet Kohli

    IPC: G06F21/57 ,  G06N3/04 ,  G06K9/62 ,  G06F16/901 ,  G06F17/16

    Abstract: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.

Patent Agency Ranking