公开(公告)号：US20230021497A1

公开(公告)日：2023-01-26

申请号：US17959132

申请日：2022-10-03

Applicant: DeepMind Technologies Limited

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

IPC: G06V30/194 ,  G06N3/04 ,  G06N3/08 ,  H04N19/52 ,  G06K9/62 ,  H04N19/50 ,  G06V10/56

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：US20220319527A1

公开(公告)日：2022-10-06

申请号：US17674752

申请日：2022-02-17

Applicant: DeepMind Technologies Limited

Inventor： Cristina Garbacea ,  Aaron Gerard Antonius van den Oord ,  Yazhe Li ,  Sze Chie Lim ,  Alejandro Luebs ,  Oriol Vinyals ,  Thomas Chadwick Walters

IPC: G10L19/16 ,  G06N3/08 ,  G10L19/032 ,  G10L25/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input audio data. Only the discrete latent representation needs to be transmitted from an encoder system to a decoder system in order for the decoder system to be able to effectively to decode, i.e., reconstruct, the input audio data.

公开(公告)号：US20220284546A1

公开(公告)日：2022-09-08

申请号：US17751359

申请日：2022-05-23

Applicant: DeepMind Technologies Limited

Inventor： Nal Emmerich Kalchbrenner ,  Daniel Belov ,  Sergio Gomez Colmenarejo ,  Aaron Gerard Antonius van den Oord ,  Ziyu Wang ,  Joao Ferdinando Gomes de Freitas ,  Scott Ellison Reed

IPC: G06T3/40 ,  G06N20/00 ,  G06N3/04

Abstract: A method of generating an output image having an output resolution of N pixels×N pixels, each pixel in the output image having a respective color value for each of a plurality of color channels, the method comprising: obtaining a low-resolution version of the output image; and upscaling the low-resolution version of the output image to generate the output image having the output resolution by repeatedly performing the following operations: obtaining a current version of the output image having a current K×K resolution; and processing the current version of the output image using a set of convolutional neural networks that are specific to the current resolution to generate an updated version of the output image having a 2K×2K resolution.

公开(公告)号：US11257507B2

公开(公告)日：2022-02-22

申请号：US16746703

申请日：2020-01-17

Applicant: DeepMind Technologies Limited

Inventor： Cristina Garbacea ,  Aaron Gerard Antonius van den Oord ,  Yazhe Li ,  Sze Chie Lim ,  Alejandro Luebs ,  Oriol Vinyals ,  Thomas Chadwick Walters

IPC: G10L19/16 ,  G10L19/032 ,  G10L25/30 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input audio data. Only the discrete latent representation needs to be transmitted from an encoder system to a decoder system in order for the decoder system to be able to effectively to decode, i.e., reconstruct, the input audio data.

公开(公告)号：US10803884B2

公开(公告)日：2020-10-13

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: G10L13/00 ,  G10L25/30 ,  G06N3/04 ,  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：US20200250528A1

公开(公告)日：2020-08-06

申请号：US16758461

申请日：2018-10-25

Applicant: DeepMind Technologies Limited

Inventor： Aaron Gerard Antonius van den Oord ,  Yutian Chen ,  Danilo Jimenez Rezende ,  Oriol Vinyals ,  Joao Ferdinando Gomes de Freitas ,  Scott Ellison Reed

IPC: G06N3/08

Abstract: A system comprising a causal convolutional neural network to autoregressively generate a succession of values of a data item conditioned upon previously generated values of the data item. The system includes support memory for a set of support data patches each of which comprises an encoding of an example data item. A soft attention mechanism attends to one or more patches when generating the current item value. The soft attention mechanism determines a set of scores for the support data patches, for example in the form of a soft attention query vector dependent upon the previously generated values of the data item. The soft attention query vector is used to query the memory. When generating the value of the data item at a current iteration layers of the causal convolutional neural network are conditioned upon the support data patches weighted by the scores.

公开(公告)号：US10304477B2

公开(公告)日：2019-05-28

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: G10L13/00 ,  G10L25/30 ,  G06N3/04 ,  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：US20190108833A1

公开(公告)日：2019-04-11

申请号：US16209661

申请日：2018-12-04

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: G10L15/16 ,  G06N3/04 ,  G06N3/08 ,  G10L15/22 ,  G10L15/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing speech recognition by generating a neural network output from an audio data input sequence, where the neural network output characterizes words spoken in the audio data input sequence. One of the methods includes, for each of the audio data inputs, providing a current audio data input sequence that comprises the audio data input and the audio data inputs preceding the audio data input in the audio data input sequence to a convolutional subnetwork comprising a plurality of dilated convolutional neural network layers, wherein the convolutional subnetwork is configured to, for each of the plurality of audio data inputs: receive the current audio data input sequence for the audio data input, and process the current audio data input sequence to generate an alternative representation for the audio data input.

公开(公告)号：US20240354566A1

公开(公告)日：2024-10-24

申请号：US18623952

申请日：2024-04-01

Applicant: DeepMind Technologies Limited

Inventor： Koray Kavukcuoglu ,  Aaron Gerard Antonius van den Oord ,  Oriol Vinyals

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input data items. One of the methods includes receiving an input data item; providing the input data item as input to an encoder neural network to obtain an encoder output for the input data item; and generating a discrete latent representation of the input data item from the encoder output, comprising: for each of the latent variables, determining, from a set of latent embedding vectors in the memory, a latent embedding vector that is nearest to the encoded vector for the latent variable.

公开(公告)号：US11948075B2

公开(公告)日：2024-04-02

申请号：US16620815

申请日：2018-06-11

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： Koray Kavukcuoglu ,  Aaron Gerard Antonius van den Oord ,  Oriol Vinyals

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input data items. One of the methods includes receiving an input data item; providing the input data item as input to an encoder neural network to obtain an encoder output for the input data item; and generating a discrete latent representation of the input data item from the encoder output, comprising: for each of the latent variables, determining, from a set of latent embedding vectors in the memory, a latent embedding vector that is nearest to the encoded vector for the latent variable.