公开(公告)号：US20180365554A1

公开(公告)日：2018-12-20

申请号：US15985463

申请日：2018-05-21

Applicant: DeepMind Technologies Limited

Inventor： Aaron Gerard Antonius van den Oord ,  Karen Simonyan ,  Oriol Vinyals

IPC: G06N3/04 ,  G06N3/08

Abstract: A feedforward generative neural network that generates an output example that includes multiple output samples of a particular type in a single neural network inference. Optionally, the generation may be conditioned on a context input. For example, the feedforward generative neural network may generate a speech waveform that is a verbalization of an input text segment conditioned on linguistic features of the text segment.

公开(公告)号：US20180336455A1

公开(公告)日：2018-11-22

申请号：US15985628

申请日：2018-05-21

Applicant: DeepMind Technologies Limited

Inventor： Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Erich Konrad Elsen

IPC: G06N3/04

CPC classification number: G06N3/088 ,  G06N3/0454

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. One of the methods includes receiving a request to generate an output example of a particular type, accessing dependency data, and generating the output example by, at each of a plurality of generation time steps: identifying one or more current blocks for the generation time step, wherein each current block is a block for which the values of the bits in all of the other blocks identified in the dependency for the block have already been generated; and generating the values of the bits in the current blocks for the generation time step conditioned on, for each current block, the already generated values of the bits in the other blocks identified in the dependency for the current block.

公开(公告)号：US20180322891A1

公开(公告)日：2018-11-08

申请号：US16030742

申请日：2018-07-09

Applicant: DeepMind Technologies Limited

Inventor： Aaron Gerard Antonius van den Oord ,  Sander Etienne Lea Dieleman ,  Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Oriol Vinyals

IPC: G10L25/30 ,  G06N3/04

CPC classification number: G10L25/30 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/0481 ,  G10H2250/311 ,  G10L13/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output sequence of audio data that comprises a respective audio sample at each of a plurality of time steps. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.

公开(公告)号：US12299574B2

公开(公告)日：2025-05-13

申请号：US18487428

申请日：2023-10-16

Applicant: DeepMind Technologies Limited

Inventor： Hubert Josef Soyer ,  Lasse Espeholt ,  Karen Simonyan ,  Yotam Doron ,  Vlad Firoiu ,  Volodymyr Mnih ,  Koray Kavukcuoglu ,  Remi Munos ,  Thomas Ward ,  Timothy James Alexander Harley ,  Iain Robert Dunning

IPC: G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.

公开(公告)号：US20250117652A1

公开(公告)日：2025-04-10

申请号：US18912978

申请日：2024-10-11

Applicant: DeepMind Technologies Limited

Inventor： Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Erich Konrad Elsen

IPC: G06N3/08 ,  G06F18/2113 ,  G06N3/045 ,  G06N3/063 ,  H03K19/173

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. Each output example includes multiple N-bit output values. To generate a given N-bit output value, a first recurrent input comprising the preceding N-bit output value is processed using a recurrent neural network and in accordance with a hidden state to generate a first score distribution. Then, values for the first half of the N bits are selected. A second recurrent input comprising (i) the preceding N-bit output value and (ii) the values for the first half of the N bits are processed using the recurrent neural network and in accordance with the same hidden state to generate a second score distribution. The values for the second half of the N bits of the output value are then selected using the second score distribution.

公开(公告)号：US12267518B2

公开(公告)日：2025-04-01

申请号：US18406837

申请日：2024-01-08

Applicant: DeepMind Technologies Limited

Inventor： Aaron Gerard Antonius van den Oord ,  Nal Emmerich Kalchbrenner ,  Karen Simonyan

IPC: H04N19/50 ,  G06F18/2113 ,  G06N3/04 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06V10/56 ,  G06V30/194 ,  H04N19/172 ,  H04N19/182 ,  H04N19/186 ,  H04N19/52

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating images using neural networks. One of the methods includes generating the output image pixel by pixel from a sequence of pixels taken from the output image, comprising, for each pixel in the output image, generating a respective score distribution over a discrete set of possible color values for each of the plurality of color channels.

公开(公告)号：US20240146948A1

公开(公告)日：2024-05-02

申请号：US18406837

申请日：2024-01-08

Applicant: DeepMind Technologies Limited

Inventor： Aaron Gerard Antonius van den Oord ,  Nal Emmerich Kalchbrenner ,  Karen Simonyan

IPC: H04N19/50 ,  G06F18/2113 ,  G06N3/04 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06V10/56 ,  G06V30/194 ,  H04N19/52

CPC classification number: H04N19/50 ,  G06F18/2113 ,  G06N3/04 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06V10/56 ,  G06V30/194 ,  H04N19/52 ,  H04N19/186

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating images using neural networks. One of the methods includes generating the output image pixel by pixel from a sequence of pixels taken from the output image, comprising, for each pixel in the output image, generating a respective score distribution over a discrete set of possible color values for each of the plurality of color channels.

公开(公告)号：US20240127060A1

公开(公告)日：2024-04-18

申请号：US18487428

申请日：2023-10-16

Applicant: DeepMind Technologies Limited

Inventor： Hubert Josef Soyer ,  Lasse Espeholt ,  Karen Simonyan ,  Yotam Doron ,  Vlad Firoiu ,  Volodymyr Mnih ,  Koray Kavukcuoglu ,  Remi Munos ,  Thomas Ward ,  Timothy James Alexander Harley ,  Iain Robert Dunning

IPC: G06N3/08 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.

公开(公告)号：US20230153617A1

公开(公告)日：2023-05-18

申请号：US18149771

申请日：2023-01-04

Applicant: DeepMind Technologies Limited

Inventor： Hubert Josef Soyer ,  Lasse Espeholt ,  Karen Simonyan ,  Yotam Doron ,  Vlad Firoiu ,  Volodymyr Mnih ,  Koray Kavukcuoglu ,  Remi Munos ,  Thomas Ward ,  Timothy James Alexander Harley ,  Iain Robert Dunning

IPC: G06N3/08 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.

公开(公告)号：US20230053618A1

公开(公告)日：2023-02-23

申请号：US17797198

申请日：2021-02-08

Applicant: DeepMind Technologies Limited

Inventor： Pauline Luc ,  Aidan Clark ,  Sander Etienne Lea Dieleman ,  Karen Simonyan

IPC: G06T11/00 ,  G06T3/00 ,  G06T7/10 ,  G06V10/764 ,  G06V10/82 ,  G06T3/40

Abstract: A recurrent unit is proposed which, at each of a series of time steps receives a corresponding input vector and generates an output at the time step having at least one component for each of a two-dimensional array of pixels. The recurrent unit is configured, at each of the series of time steps except the first, to receive the output of the recurrent unit at the preceding time step, and to apply to the output of the recurrent unit at the preceding time step at least one convolution which depends on the input vector at the time step. The convolution further depends upon the output of the recurrent unit at the preceding time step. This convolution generates a warped dataset which has at least one component for each pixel of the array. The output of the recurrent unit at each time step is based on the warped dataset and the input vector.