公开(公告)号：US10949717B2

公开(公告)日：2021-03-16

申请号：US16537423

申请日：2019-08-09

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 ,  H04N19/18 ,  H04N19/17 ,  H04N19/186 ,  H04N19/172 ,  H04N19/182

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：US20200293899A1

公开(公告)日：2020-09-17

申请号：US16759567

申请日：2018-10-26

Applicant: DeepMind Technologies Limited

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

IPC: G06N3/08 ,  G06N3/04 ,  G06F16/901

Abstract: 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.

公开(公告)号：US10733390B2

公开(公告)日：2020-08-04

申请号：US16434459

申请日：2019-06-07

Applicant: DeepMind Technologies Limited

Inventor： Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Lasse Espeholt

IPC: G06F40/58 ,  G06N3/04 ,  G06F40/44 ,  G06N3/08 ,  G10L15/197

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for language modeling. In one aspect, a system comprises: a masked convolutional decoder neural network that comprises a plurality of masked convolutional neural network layers and is configured to generate a respective probability distribution over a set of possible target embeddings at each of a plurality of time steps; and a modeling engine that is configured to use the respective probability distribution generated by the decoder neural network at each of the plurality of time steps to estimate a probability that a string represented by the target embeddings corresponding to the plurality of time steps belongs to the natural language.

公开(公告)号：US20190286708A1

公开(公告)日：2019-09-19

申请号：US16434459

申请日：2019-06-07

Applicant: DeepMind Technologies Limited

Inventor： Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Lasse Espeholt

IPC: G06F17/28 ,  G10L15/197 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural machine translation. In one aspect, a system is configured to receive an input sequence of source embeddings representing a source sequence of words in a source natural language and to generate an output sequence of target embeddings representing a target sequence of words that is a translation of the source sequence into a target natural language, the system comprising: a dilated convolutional neural network configured to process the input sequence of source embeddings to generate an encoded representation of the source sequence, and a masked dilated convolutional neural network configured to process the encoded representation of the source sequence to generate the output sequence of target embeddings.

公开(公告)号：US20190251987A1

公开(公告)日：2019-08-15

申请号：US16390549

申请日：2019-04-22

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 ,  G10L13/06 ,  G06N3/04

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：US20180329897A1

公开(公告)日：2018-11-15

申请号：US16032971

申请日：2018-07-11

Applicant: DeepMind Technologies Limited

Inventor： Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Lasse Espeholt

IPC: G06F17/28 ,  G06N3/04 ,  G06N3/08 ,  G10L15/197

CPC classification number: G06F17/289 ,  G06F17/2818 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/084 ,  G10L15/197

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural machine translation. In one aspect, a system is configured to receive an input sequence of source embeddings representing a source sequence of words in a source natural language and to generate an output sequence of target embeddings representing a target sequence of words that is a translation of the source sequence into a target natural language, the system comprising: a dilated convolutional neural network configured to process the input sequence of source embeddings to generate an encoded representation of the source sequence, and a masked dilated convolutional neural network configured to process the encoded representation of the source sequence to generate the output sequence of target embeddings.

公开(公告)号：US10032089B2

公开(公告)日：2018-07-24

申请号：US15174133

申请日：2016-06-06

Applicant: DeepMind Technologies Limited

Inventor： Maxwell Elliot Jaderberg ,  Karen Simonyan ,  Andrew Zisserman ,  Koray Kavukcuoglu

IPC: G06K9/46 ,  G06K9/36 ,  G06N3/02 ,  G06K9/52 ,  G06N3/04 ,  G06K9/03 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using an image processing neural network system that includes a spatial transformer module. One of the methods includes receiving an input feature map derived from the one or more input images, and applying a spatial transformation to the input feature map to generate a transformed feature map, comprising: processing the input feature map to generate spatial transformation parameters for the spatial transformation, and sampling from the input feature map in accordance with the spatial transformation parameters to generate the transformed feature map.

公开(公告)号：US20240249146A1

公开(公告)日：2024-07-25

申请号：US18415376

申请日：2024-01-17

Applicant: DeepMind Technologies Limited

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

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

CPC classification number: G06N3/086 ,  G06F16/9024 ,  G06N3/045 ,  G06F17/15

Abstract: 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.

公开(公告)号：US20240135955A1

公开(公告)日：2024-04-25

申请号：US18519986

申请日：2023-11-27

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 ,  G06N3/045 ,  G06N3/048 ,  G10L13/06

CPC classification number: G10L25/30 ,  G06N3/04 ,  G06N3/045 ,  G06N3/048 ,  G10L13/06 ,  G10H2250/311

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：US11875269B2

公开(公告)日：2024-01-16

申请号：US16882352

申请日：2020-05-22

Applicant: DeepMind Technologies Limited

Inventor： Jeffrey Donahue ,  Karen Simonyan

IPC: G06N3/088 ,  G06N3/045

CPC classification number: G06N3/088 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a generator neural network and an encoder neural network. The generator neural network generates, based on a set of latent values, data items which are samples of a distribution. The encoder neural network generates a set of latent values for a respective data item. The training method comprises jointly training the generator neural network, the encoder neural network and a discriminator neural network configured to distinguish between samples generated by the generator network and samples of the distribution which are not generated by the generator network. The discriminator neural network is configured to distinguish by processing, by the discriminator neural network, an input pair comprising a sample part and a latent part.