公开(公告)号：US20220180147A1

公开(公告)日：2022-06-09

申请号：US17441463

申请日：2020-05-19

Applicant: DeepMind Technologies Limited

Inventor： Sergey Bartunov ,  Jack William Rae ,  Timothy Paul Lillicrap ,  Simon Osindero

IPC: G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing associative memory. In one aspect a system comprises an associative memory neural network to process an input to generate an output that defines an energy corresponding to the input. A reading subsystem retrieves stored information from the associative memory neural network. The reading subsystem performs operations including receiving a given, i.e. query, input and retrieving a data element from the associative memory neural network that is associated with the given input. The retrieving is performed by iteratively adjusting the given input using the associative memory neural network.

公开(公告)号：US11580736B2

公开(公告)日：2023-02-14

申请号：US16954068

申请日：2019-01-07

Applicant: DeepMind Technologies Limited

Inventor： Simon Osindero ,  Joao Carreira ,  Viorica Patraucean ,  Andrew Zisserman

IPC: G06V20/40 ,  G06N3/04 ,  G06T1/20 ,  G06N3/049

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for parallel processing of video frames using neural networks. One of the methods includes receiving a video sequence comprising a respective video frame at each of a plurality of time steps; and processing the video sequence using a video processing neural network to generate a video processing output for the video sequence, wherein the video processing neural network includes a sequence of network components, wherein the network components comprise a plurality of layer blocks each comprising one or more neural network layers, wherein each component is active for a respective subset of the plurality of time steps, and wherein each layer block is configured to, at each time step at which the layer block is active, receive an input generated at a previous time step and to process the input to generate a block output.

公开(公告)号：US20210089908A1

公开(公告)日：2021-03-25

申请号：US17032562

申请日：2020-09-25

Applicant: DeepMind Technologies Limited

Inventor： Tom Schaul ,  Diana Luiza Borsa ,  Fengning Ding ,  David Szepesvari ,  Georg Ostrovski ,  Simon Osindero ,  William Clinton Dabney

IPC: G06N3/08 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes sampling a behavior modulation in accordance with a current probability distribution; for each of one or more time steps: processing an input comprising an observation characterizing a current state of the environment at the time step using an action selection neural network to generate a respective action score for each action in a set of possible actions that can be performed by the agent; modifying the action scores using the sampled behavior modulation; and selecting the action to be performed by the agent at the time step based on the modified action scores; determining a fitness measure corresponding to the sampled behavior modulation; and updating the current probability distribution over the set of possible behavior modulations using the fitness measure corresponding to the behavior modulation.

公开(公告)号：US20210027064A1

公开(公告)日：2021-01-28

申请号：US16954068

申请日：2019-01-07

Applicant: DeepMind Technologies Limited

Inventor： Simon Osindero ,  Joao Carreira ,  Viorica Patraucean ,  Andrew Zisserman

IPC: G06K9/00 ,  G06N3/04 ,  G06T1/20

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for parallel processing of video frames using neural networks. One of the methods includes receiving a video sequence comprising a respective video frame at each of a plurality of time steps; and processing the video sequence using a video processing neural network to generate a video processing output for the video sequence, wherein the video processing neural network includes a sequence of network components, wherein the network components comprise a plurality of layer blocks each comprising one or more neural network layers, wherein each component is active for a respective subset of the plurality of time steps, and wherein each layer block is configured to, at each time step at which the layer block is active, receive an input generated at a previous time step and to process the input to generate a block output.

公开(公告)号：US11715009B2

公开(公告)日：2023-08-01

申请号：US16303595

申请日：2017-05-19

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： Oriol Vinyals ,  Alexander Benjamin Graves ,  Wojciech Czarnecki ,  Koray Kavukcuoglu ,  Simon Osindero ,  Maxwell Elliot Jaderberg

IPC: G06N3/084 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06N3/084 ,  G06N3/044 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network including a first subnetwork followed by a second subnetwork on training inputs by optimizing an objective function. In one aspect, a method includes processing a training input using the neural network to generate a training model output, including processing a subnetwork input for the training input using the first subnetwork to generate a subnetwork activation for the training input in accordance with current values of parameters of the first subnetwork, and providing the subnetwork activation as input to the second subnetwork; determining a synthetic gradient of the objective function for the first subnetwork by processing the subnetwork activation using a synthetic gradient model in accordance with current values of parameters of the synthetic gradient model; and updating the current values of the parameters of the first subnetwork using the synthetic gradient.

公开(公告)号：US20230186625A1

公开(公告)日：2023-06-15

申请号：US18108873

申请日：2023-02-13

Applicant: DeepMind Technologies Limited

Inventor： Simon Osindero ,  Joao Carreira ,  Viorica Patraucean ,  Andrew Zisserman

IPC: G06V20/40 ,  G06N3/049 ,  G06T1/20 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06V20/40 ,  G06N3/049 ,  G06T1/20 ,  G06N3/044 ,  G06N3/045 ,  G06T2200/28 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for parallel processing of video frames using neural networks. One of the methods includes receiving a video sequence comprising a respective video frame at each of a plurality of time steps; and processing the video sequence using a video processing neural network to generate a video processing output for the video sequence, wherein the video processing neural network includes a sequence of network components, wherein the network components comprise a plurality of layer blocks each comprising one or more neural network layers, wherein each component is active for a respective subset of the plurality of time steps, and wherein each layer block is configured to, at each time step at which the layer block is active, receive an input generated at a previous time step and to process the input to generate a block output.

公开(公告)号：US12277487B2

公开(公告)日：2025-04-15

申请号：US17441463

申请日：2020-05-19

Applicant: DeepMind Technologies Limited

Inventor： Sergey Bartunov ,  Jack William Rae ,  Timothy Paul Lillicrap ,  Simon Osindero

IPC: G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing associative memory. In one aspect a system comprises an associative memory neural network to process an input to generate an output that defines an energy corresponding to the input. A reading subsystem retrieves stored information from the associative memory neural network. The reading subsystem performs operations including receiving a given, i.e. query, input and retrieving a data element from the associative memory neural network that is associated with the given input. The retrieving is performed by iteratively adjusting the given input using the associative memory neural network.

公开(公告)号：US12175737B2

公开(公告)日：2024-12-24

申请号：US17773789

申请日：2020-11-13

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： Viorica Patraucean ,  Bilal Piot ,  Joao Carreira ,  Volodymyr Mnih ,  Simon Osindero

IPC: G06V10/82 ,  G06N3/045 ,  G06N3/048

Abstract: A system that is configured to receive a sequence of task inputs and to perform a machine learning task is described. The system includes a reinforcement learning (RL) neural network and a task neural network. The RL neural network is configured to: generate, for each task input of the sequence of task inputs, a respective decision that determines whether to encode the task input or to skip the task input, and provide the respective decision of each task input to the task neural network. The task neural network is configured to: receive the sequence of task inputs, receive, from the RL neural network, for each task input of the sequence of task inputs, a respective decision that determines whether to encode the task input or to skip the task input, process each of the un-skipped task inputs in the sequence of task inputs to generate a respective accumulated feature for the un-skipped task input, wherein the respective accumulated feature characterizes features of the un-skipped task input and of previous un-skipped task inputs in the sequence, and generate a machine learning task output for the machine learning task based on the last accumulated feature generated for the last un-skipped task input in the sequence.

公开(公告)号：US20240320506A1

公开(公告)日：2024-09-26

申请号：US18698890

申请日：2022-10-05

Applicant: DeepMind Technologies Limited

Inventor： Anirudh Goyal ,  Andrea Banino ,  Abram Luke Friesen ,  Theophane Guillaume Weber ,  Adrià Puigdomènech Badia ,  Nan Ke ,  Simon Osindero ,  Timothy Paul Lillicrap ,  Charles Blundell

IPC: G06N3/092 ,  G06N3/044 ,  G06N3/0455 ,  G06N3/084

CPC classification number: G06N3/092 ,  G06N3/044 ,  G06N3/0455 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a reinforcement learning agent in an environment to perform a task using a retrieval-augmented action selection process. One of the methods includes receiving a current observation characterizing a current state of the environment; processing an encoder network input comprising the current observation to determine a policy neural network hidden state that corresponds to the current observation; maintaining a plurality of trajectories generated as a result of the reinforcement learning agent interacting with the environment; selecting one or more trajectories from the plurality of trajectories; updating the policy neural network hidden state using update data determined from the one or more selected trajectories; and processing the updated hidden state using a policy neural network to generate a policy output that specifies an action to be performed by the agent in response to the current observation.

公开(公告)号：US11967150B2

公开(公告)日：2024-04-23

申请号：US18108873

申请日：2023-02-13

Applicant: DeepMind Technologies Limited

Inventor： Simon Osindero ,  Joao Carreira ,  Viorica Patraucean ,  Andrew Zisserman

IPC: G06V20/40 ,  G06N3/044 ,  G06N3/045 ,  G06N3/049 ,  G06T1/20

CPC classification number: G06V20/40 ,  G06N3/044 ,  G06N3/045 ,  G06N3/049 ,  G06T1/20 ,  G06T2200/28 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for parallel processing of video frames using neural networks. One of the methods includes receiving a video sequence comprising a respective video frame at each of a plurality of time steps; and processing the video sequence using a video processing neural network to generate a video processing output for the video sequence, wherein the video processing neural network includes a sequence of network components, wherein the network components comprise a plurality of layer blocks each comprising one or more neural network layers, wherein each component is active for a respective subset of the plurality of time steps, and wherein each layer block is configured to, at each time step at which the layer block is active, receive an input generated at a previous time step and to process the input to generate a block output.