公开(公告)号：US12141691B2

公开(公告)日：2024-11-12

申请号：US16968413

申请日：2019-02-11

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：US11934935B2

公开(公告)日：2024-03-19

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 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  G10L13/00

CPC classification number: G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  G10L13/00

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：US11868894B2

公开(公告)日：2024-01-09

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：US11836625B2

公开(公告)日：2023-12-05

申请号：US17948016

申请日：2022-09-19

Applicant: DeepMind Technologies Limited

Inventor： Karen Simonyan ,  David Silver ,  Julian Schrittwieser

IPC: G06N3/08 ,  G06N7/01

CPC classification number: G06N3/08 ,  G06N7/01

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network. One of the methods includes receiving an observation characterizing a current state of the environment; determining a target network output for the observation by performing a look ahead search of possible future states of the environment starting from the current state until the environment reaches a possible future state that satisfies one or more termination criteria, wherein the look ahead search is guided by the neural network in accordance with current values of the network parameters; selecting an action to be performed by the agent in response to the observation using the target network output generated by performing the look ahead search; and storing, in an exploration history data store, the target network output in association with the observation for use in updating the current values of the network parameters.

公开(公告)号：US11693627B2

公开(公告)日：2023-07-04

申请号：US16955420

申请日：2019-02-11

Applicant: DeepMind Technologies Limited

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

IPC: G06F7/00 ,  G06F7/523 ,  G06N3/08

CPC classification number: G06F7/523 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using neural networks having contiguous sparsity patterns. One of the methods includes storing a first parameter matrix of a neural network having a contiguous sparsity pattern in storage associated with a computing device. The computing device performs an inference pass of the neural network to generate an output vector, including reading, from the storage associated with the computing device, one or more activation values from the input vector, reading, from the storage associated with the computing device, a block of non-zero parameter values, and multiplying each of the one or more activation values by one or more of the block of non-zero parameter values.

公开(公告)号：US11676035B2

公开(公告)日：2023-06-13

申请号：US16751169

申请日：2020-01-23

Applicant: DeepMind Technologies Limited

Inventor： Karel Lenc ,  Karen Simonyan ,  Tom Schaul ,  Erich Konrad Elsen

IPC: G06N3/08 ,  G06N3/086 ,  G06N3/044

CPC classification number: G06N3/086 ,  G06N3/08 ,  G06N3/044

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. The neural network has a plurality of differentiable weights and a plurality of non-differentiable weights. One of the methods includes determining trained values of the plurality of differentiable weights and the non-differentiable weights by repeatedly performing operations that include determining an update to the current values of the plurality of differentiable weights using a machine learning gradient-based training technique and determining, using an evolution strategies (ES) technique, an update to the current values of a plurality of distribution parameters.

公开(公告)号：US20210407625A1

公开(公告)日：2021-12-30

申请号：US17266689

申请日：2019-09-16

Applicant: DeepMind Technologies Limited

Inventor： Andrew W. Senior ,  James Kirkpatrick ,  Laurent Sifre ,  Richard Andrew Evans ,  Hugo Penedones ,  Chongli Qin ,  Ruoxi Sun ,  Karen Simonyan ,  John Jumper

IPC: G16B40/20 ,  G16H10/40 ,  G16B15/20 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises generating a distance map for a given protein, wherein the given protein is defined by a sequence of amino acid residues arranged in a structure, wherein the distance map characterizes estimated distances between the amino acid residues in the structure, comprising: generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein the first positions are a proper subset of the sequence; and generating the distance map for the given protein using the plurality of distance map crops.

公开(公告)号：US20210342670A1

公开(公告)日：2021-11-04

申请号：US17375250

申请日：2021-07-14

Applicant: DeepMind Technologies Limited

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

IPC: G06N3/04 ,  G10L15/16 ,  G10L13/08 ,  G10L25/30 ,  G10L13/04 ,  G06N3/08 ,  G06F40/44 ,  G06F40/279

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing sequences using convolutional neural networks. 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：US11144782B2

公开(公告)日：2021-10-12

申请号：US16338338

申请日：2017-09-29

Applicant: DeepMind Technologies Limited

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

IPC: G06K9/62 ,  G06K9/46 ,  G06N3/04 ,  G06K9/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating video frames using neural networks. One of the methods includes processing a sequence of video frames using an encoder neural network to generate an encoded representation; and generating a predicted next frame pixel by pixel according to a pixel order and a channel order, comprising: for each color channel of each pixel, providing as input to a decoder neural network (i) the encoded representation, (ii) color values for any pixels before the pixel in the pixel order, and (iii) color values for the pixel for any color channels before the color channel in the channel order, wherein the decoder neural network is configured to generate an output defining a score distribution over a plurality of possible color values, and determining the color value for the color channel of the pixel by sampling from the score distribution.

公开(公告)号：US20210192298A1

公开(公告)日：2021-06-24

申请号：US17198096

申请日：2021-03-10

Applicant: DeepMind Technologies Limited

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

IPC: G06K9/66 ,  G06N3/04 ,  G06N3/08 ,  G06K9/46 ,  H04N19/52 ,  G06K9/62 ,  H04N19/50

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.