利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

535 条记录 (耗时 0.028 秒)

    TRAINING AGENT NEURAL NETWORKS THROUGH OPEN-ENDED LEARNING
    2.
    发明公开
    TRAINING AGENT NEURAL NETWORKS THROUGH OPEN-ENDED LEARNING 审中-公开

    公开(公告)号：US20240330701A1

    公开(公告)日：2024-10-03

    申请号：US18577484

    申请日：2022-07-27

    申请人： DeepMind Technologies Limited

    发明人： Maxwell Elliot Jaderberg ,  Wojciech Czarnecki

    IPC分类号： G06N3/092 ,  G06N3/0985

    CPC分类号： G06N3/092 ,  G06N3/0985

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for raining an agent neural network for use in controlling an agent to perform a plurality of tasks. One of the methods includes maintaining population data specifying a population of one or more candidate agent neural networks; and training each candidate agent neural network on a respective set of one or more tasks to update the parameter values of the parameters of the candidate agent neural networks in the population data, the training comprising, for each candidate agent neural network: obtaining data identifying a candidate task; obtaining data specifying a control policy for the candidate task; determining whether to train the candidate agent neural network on the candidate task; and in response to determining to train the candidate agent neural network on the candidate task, training the candidate agent neural network on the candidate task.

    GENERATING ENVIRONMENT MODELS USING IN-CONTEXT ADAPTATION AND EXPLORATION
    4.
    发明公开
    GENERATING ENVIRONMENT MODELS USING IN-CONTEXT ADAPTATION AND EXPLORATION 审中-公开

    公开(公告)号：US20240256884A1

    公开(公告)日：2024-08-01

    申请号：US18424687

    申请日：2024-01-26

    申请人： DeepMind Technologies Limited

    发明人： Hado Philip van Hasselt ,  Nan Ke ,  Chentian Jiang

    IPC分类号： G06N3/092 ,  G06N3/042

    CPC分类号： G06N3/092 ,  G06N3/042

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent interacting with an environment to perform a task. In one aspect, one of the methods include: maintaining context data; receiving a current observation characterizing a current state of the environment; generating a current graph model that represents the environment; selecting, from a possible set of actions and using the current graph model, a current action to be performed by the agent in response to the current observation; controlling the agent to perform the selected current action to cause the environment to transition from the current state into a new state; and updating the context data to include (i) data identifying the selected current action and (ii) a new observation characterizing the new state of the environment.

    Using Hierarchical Representations for Neural Network Architecture Searching
    5.
    发明公开
    Using Hierarchical Representations for Neural Network Architecture Searching 审中-公开

    公开(公告)号：US20240249146A1

    公开(公告)日：2024-07-25

    申请号：US18415376

    申请日：2024-01-17

    申请人： DeepMind Technologies Limited

    发明人： Chrisantha Thomas Fernando ,  Karen Simonyan ,  Koray Kavukcuoglu ,  Hanxiao Liu ,  Oriol Vinyals

    IPC分类号： G06N3/086 ,  G06F16/901 ,  G06F17/15 ,  G06N3/045

    CPC分类号： G06N3/086 ,  G06F16/9024 ,  G06N3/045 ,  G06F17/15

    摘要： A computer-implemented method for automatically determining a neural network architecture represents a neural network architecture as a data structure defining a hierarchical set of directed acyclic graphs in multiple levels. Each graph has an input, an output, and a plurality of nodes between the input and the output. At each level, a corresponding set of the nodes are connected pairwise by directed edges which indicate operations performed on outputs of one node to generate an input to another node. Each level is associated with a corresponding set of operations. At a lowest level, the operations associated with each edge are selected from a set of primitive operations. The method includes repeatedly generating new sample neural network architectures, and evaluating their fitness. The modification is performed by selecting a level, selecting two nodes at that level, and modifying, removing or adding an edge between those nodes according to operations associated with lower levels of the hierarchy.

    Compressed sensing using neural networks
    6.
    发明授权
    Compressed sensing using neural networks 有权

    公开(公告)号：US12032523B2

    公开(公告)日：2024-07-09

    申请号：US16818895

    申请日：2020-03-13

    申请人： DeepMind Technologies Limited

    发明人： Yan Wu ,  Timothy Paul Lillicrap ,  Mihaela Rosca

    IPC分类号： G06F16/174 ,  G06N3/045 ,  G06N3/08

    CPC分类号： G06F16/1744 ,  G06N3/045 ,  G06N3/08

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for compressed sensing using neural networks. One of the methods includes receiving an input measurement of an input data item; for each of one or more optimization steps: processing a latent representation using a generator neural network to generate a candidate reconstructed data item, processing the candidate reconstructed data item using a measurement neural network to generate a measurement of the candidate reconstructed data item, and updating the latent representation to reduce an error between the measurement and the input measurement; and processing the latent representation after the one or more optimization steps using the generator neural network to generate a reconstruction of the input data item.

    Low latency multi-constraint ranking of content items
    8.
    发明授权
    Low latency multi-constraint ranking of content items 有权

    公开(公告)号：US12001484B2

    公开(公告)日：2024-06-04

    申请号：US17177097

    申请日：2021-02-16

    申请人： DeepMind Technologies Limited

    发明人： Timothy Arthur Mann ,  Ivan Lobov ,  Anton Zhernov ,  Krishnamurthy Dvijotham ,  Xiaohong Gong ,  Dan-Andrei Calian

    IPC分类号： G06F16/95 ,  G06F16/903 ,  G06F17/11 ,  G06F17/16

    CPC分类号： G06F16/90335 ,  G06F17/11 ,  G06F17/16

    摘要： Methods and systems for low-latency multi-constraint ranking of content items. One of the methods includes receiving a request to rank a plurality of content items for presentation to a user to maximize a primary objective subject to a plurality of constraints; initializing a dual variable vector; updating the dual variable vector, comprising: determining an overall objective score for the dual variable vector; identifying a plurality of candidate dual variable vectors that includes one or more neighboring node dual variable vectors; determining respective overall objective scores for each of the one or more candidate dual variable vectors; identifying the candidate with the best overall objective score; and determining whether to update the dual variable vector based on whether the identified candidate has a better overall objective score than the dual variable vector; and determining a final ranking for the content items based on the dual variable vector.

    TRAINING GRAPH NEURAL NETWORKS USING A DE-NOISING OBJECTIVE
    9.
    发明公开
    TRAINING GRAPH NEURAL NETWORKS USING A DE-NOISING OBJECTIVE 审中-公开

    公开(公告)号：US20240176982A1

    公开(公告)日：2024-05-30

    申请号：US18283131

    申请日：2022-05-30

    申请人： DeepMind Technologies Limited

    发明人： Jonathan William Godwin ,  Peter William Battaglia ,  Kevin Michael Schaarschmidt ,  Alvaro Sanchez

    IPC分类号： G06N3/04 ,  G06N3/084

    CPC分类号： G06N3/04 ,  G06N3/084

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network that includes one or more graph neural network layers. In one aspect, a method comprises: generating data defining a graph, comprising: generating a respective final feature representation for each node, wherein, for each of one or more of the nodes, the respective final feature representation is a modified feature representation that is generated from a respective feature representation for the node using respective noise; processing the data defining the graph using one or more of the graph neural network layers of the neural network to generate a respective updated node embedding of each node; and processing, for each of one or more of the nodes having modified feature representations, the updated node embedding of the node to generate a respective de-noising prediction for the node.