公开(公告)号：US20190266475A1

公开(公告)日：2019-08-29

申请号：US16403352

申请日：2019-05-03

Applicant: DeepMind Technologies Limited

Inventor： Daniel Pieter Wierstra ,  Shakir Mohamed ,  Silvia Chiappa ,  Sebastien Henri Andre Racaniere

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

公开(公告)号：US20190213469A1

公开(公告)日：2019-07-11

申请号：US16241334

申请日：2019-01-07

Applicant: DeepMind Technologies Limited

Inventor： Ivo Danihelka ,  Danilo Jimenez Rezende ,  Shakir Mohamed

IPC: G06N3/04 ,  G06N3/08 ,  G06K9/62 ,  G06K9/66

CPC classification number: G06N3/0445 ,  G06K9/6257 ,  G06K9/66 ,  G06N3/0472 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network system. In one aspect, a neural network system includes a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the latent variables to update a hidden state of the recurrent neural network; and a generative subsystem that is configured to, for each time step, generate the set of latent variables for the time step and provide the set of latent variables as input to the recurrent neural network; update a hidden canvas using the updated hidden state of the recurrent neural network; and, for a last time step, generate an output image using the updated hidden canvas for the last time step.

公开(公告)号：US20200342289A1

公开(公告)日：2020-10-29

申请号：US16893565

申请日：2020-06-05

Applicant: DeepMind Technologies Limited

Inventor： Daniel Pieter Wierstra ,  Shakir Mohamed ,  Silvia Chiappa ,  Sebastien Henri Andre Racaniere

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

公开(公告)号：US11200482B2

公开(公告)日：2021-12-14

申请号：US16893565

申请日：2020-06-05

Applicant: DeepMind Technologies Limited

Inventor： Daniel Pieter Wierstra ,  Shakir Mohamed ,  Silvia Chiappa ,  Sebastien Henri Andre Racaniere

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

公开(公告)号：US10713559B2

公开(公告)日：2020-07-14

申请号：US16403352

申请日：2019-05-03

Applicant: DeepMind Technologies Limited

Inventor： Daniel Pieter Wierstra ,  Shakir Mohamed ,  Silvia Chiappa ,  Sebastien Henri Andre Racaniere

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

公开(公告)号：US10373055B1

公开(公告)日：2019-08-06

申请号：US15600696

申请日：2017-05-19

Applicant: DeepMind Technologies Limited

Inventor： Loic Matthey-de-l'Endroit ,  Arka Tilak Pal ,  Shakir Mohamed ,  Xavier Glorot ,  Irina Higgins ,  Alexander Lerchner

IPC: G06K9/46 ,  G06N3/08 ,  G06N3/04 ,  G06F17/18

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a variational auto-encoder (VAE) to generate disentangled latent factors on unlabeled training images. In one aspect, a method includes receiving the plurality of unlabeled training images, and, for each unlabeled training image, processing the unlabeled training image using the VAE to determine the latent representation of the unlabeled training image and to generate a reconstruction of the unlabeled training image in accordance with current values of the parameters of the VAE, and adjusting current values of the parameters of the VAE by optimizing a loss function that depends on a quality of the reconstruction and also on a degree of independence between the latent factors in the latent representation of the unlabeled training image.

公开(公告)号：US10657436B2

公开(公告)日：2020-05-19

申请号：US16241334

申请日：2019-01-07

Applicant: DeepMind Technologies Limited

Inventor： Ivo Danihelka ,  Danilo Jimenez Rezende ,  Shakir Mohamed

IPC: G06N3/04 ,  G06K9/62 ,  G06K9/66 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network system. In one aspect, a neural network system includes a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the latent variables to update a hidden state of the recurrent neural network; and a generative subsystem that is configured to, for each time step, generate the set of latent variables for the time step and provide the set of latent variables as input to the recurrent neural network; update a hidden canvas using the updated hidden state of the recurrent neural network; and, for a last time step, generate an output image using the updated hidden canvas for the last time step.

公开(公告)号：US10176424B2

公开(公告)日：2019-01-08

申请号：US15424708

申请日：2017-02-03

Applicant: DeepMind Technologies Limited

Inventor： Ivo Danihelka ,  Danilo Jimenez Rezende ,  Shakir Mohamed

IPC: G06K9/00 ,  G06N3/04 ,  G06K9/62 ,  G06K9/66 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network system. In one aspect, a neural network system includes a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the latent variables to update a hidden state of the recurrent neural network; and a generative subsystem that is configured to, for each time step, generate the set of latent variables for the time step and provide the set of latent variables as input to the recurrent neural network; update a hidden canvas using the updated hidden state of the recurrent neural network; and, for a last time step, generate an output image using the updated hidden canvas for the last time step.