-
公开(公告)号:US11870947B2
公开(公告)日:2024-01-09
申请号:US17959132
申请日:2022-10-03
Applicant: DeepMind Technologies Limited
IPC: H04N19/50 , H04N19/52 , H04N19/56 , G06N3/04 , G06N3/08 , G06F18/21 , G06V10/56 , G06V30/19 , G06N3/084 , G06F18/2113 , G06N3/044 , G06N3/045 , G06V30/194 , H04N19/186 , H04N19/172 , H04N19/182
CPC classification number: H04N19/50 , G06F18/2113 , G06N3/04 , G06N3/044 , G06N3/045 , G06N3/08 , G06N3/084 , G06V10/56 , G06V30/194 , H04N19/52 , H04N19/172 , H04N19/182 , 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:US11853861B2
公开(公告)日:2023-12-26
申请号:US17962881
申请日:2022-10-10
Applicant: DeepMind Technologies Limited
Inventor: Nal Emmerich Kalchbrenner , Karen Simonyan , Erich Konrad Elsen
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:US11462034B2
公开(公告)日:2022-10-04
申请号:US17198096
申请日:2021-03-10
Applicant: DeepMind Technologies Limited
IPC: G06V30/194 , G06N3/04 , G06N3/08 , H04N19/52 , H04N19/50 , G06V10/56 , H04N19/186 , H04N19/172 , H04N19/182 , G06K9/62
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:US11361403B2
公开(公告)日:2022-06-14
申请号:US16324061
申请日:2018-02-26
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
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:US11080591B2
公开(公告)日:2021-08-03
申请号:US15697407
申请日:2017-09-06
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 , G06F17/18
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:US20200342183A1
公开(公告)日:2020-10-29
申请号:US16927267
申请日:2020-07-13
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:US11948066B2
公开(公告)日:2024-04-02
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 , G06F40/279 , G06F40/44 , G06N3/044 , G06N3/045 , G06N3/047 , G06N3/084 , G10L13/04 , G10L13/08 , G10L15/16 , G10L25/30 , G06F17/18
CPC classification number: G06N3/047 , G06F40/279 , G06F40/44 , G06N3/044 , G06N3/045 , G06N3/084 , G10L13/04 , G10L13/086 , G10L15/16 , G10L25/30 , G06F17/18 , G10H2250/311
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:US11069345B2
公开(公告)日:2021-07-20
申请号:US16719424
申请日:2019-12-18
Applicant: DeepMind Technologies Limited
Inventor: Aaron Gerard Antonius van den Oord , Sander Etienne Lea Dieleman , Nal Emmerich Kalchbrenner , Karen Simonyan , Oriol Vinyals , Lasse Espeholt
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:US11010663B2
公开(公告)日:2021-05-18
申请号:US15395553
申请日:2016-12-30
Applicant: DeepMind Technologies Limited
Inventor: Ivo Danihelka , Nal Emmerich Kalchbrenner , Gregory Duncan Wayne , Benigno Uría-Martínez , Alexander Benjamin Graves
Abstract: Systems, methods, and apparatus, including computer programs encoded on a computer storage medium, related to associative long short-term memory (LSTM) neural network layers configured to maintain N copies of an internal state for the associative LSTM layer, N being an integer greater than one. In one aspect, a system includes a recurrent neural network including an associative LSTM layer, wherein the associative LSTM layer is configured to, for each time step, receive a layer input, update each of the N copies of the internal state using the layer input for the time step and a layer output generated by the associative LSTM layer for a preceding time step, and generate a layer output for the time step using the N updated copies of the internal state.
-
公开(公告)号:US10586531B2
公开(公告)日:2020-03-10
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
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.
-
-
-
-
-
-
-
-
-