公开(公告)号：US11354548B1

公开(公告)日：2022-06-07

申请号：US16927159

申请日：2020-07-13

Applicant: DeepMind Technologies Limited

Inventor： Volodymyr Mnih ,  Koray Kavukcuoglu

IPC: G06K9/62 ,  G06V10/44 ,  G06V20/80 ,  G06V30/194 ,  G06V30/413

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using recurrent attention. One of the methods includes determining a location in the first image; extracting a glimpse from the first image using the location; generating a glimpse representation of the extracted glimpse; processing the glimpse representation using a recurrent neural network to update a current internal state of the recurrent neural network to generate a new internal state; processing the new internal state to select a location in a next image in the image sequence after the first image; and processing the new internal state to select an action from a predetermined set of possible actions.

公开(公告)号：US11334792B2

公开(公告)日：2022-05-17

申请号：US16403388

申请日：2019-05-03

Applicant: DeepMind Technologies Limited

Inventor： Volodymyr Mnih ,  Adria Puigdomenech Badia ,  Alexander Benjamin Graves ,  Timothy James Alexander Harley ,  David Silver ,  Koray Kavukcuoglu

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network.

公开(公告)号：US10949734B2

公开(公告)日：2021-03-16

申请号：US15396319

申请日：2016-12-30

Applicant: DeepMind Technologies Limited

Inventor： Neil Charles Rabinowitz ,  Guillaume Desjardins ,  Andrei-Alexandru Rusu ,  Koray Kavukcuoglu ,  Raia Thais Hadsell ,  Razvan Pascanu ,  James Kirkpatrick ,  Hubert Josef Soyer

IPC: G06N3/04 ,  G06N3/08 ,  G06F17/16

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

公开(公告)号：US10762421B2

公开(公告)日：2020-09-01

申请号：US15174020

申请日：2016-06-06

Applicant: DeepMind Technologies Limited

Inventor： Guillaume Desjardins ,  Karen Simonyan ,  Koray Kavukcuoglu ,  Razvan Pascanu

IPC: G06N3/08 ,  G06N20/00 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a whitened neural network layer. One of the methods includes receiving an input activation generated by a layer before the whitened neural network layer in the sequence; processing the received activation in accordance with a set of whitening parameters to generate a whitened activation; processing the whitened activation in accordance with a set of layer parameters to generate an output activation; and providing the output activation as input to a neural network layer after the whitened neural network layer in the sequence.

公开(公告)号：US20200184316A1

公开(公告)日：2020-06-11

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: G06N3/04 ,  G06N3/08

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：US10679126B2

公开(公告)日：2020-06-09

申请号：US16511571

申请日：2019-07-15

Applicant: DeepMind Technologies Limited

Inventor： Simon Osindero ,  Koray Kavukcuoglu ,  Alexander Vezhnevets

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a system configured to select actions to be performed by an agent that interacts with an environment. The system comprises a manager neural network subsystem and a worker neural network subsystem. The manager subsystem is configured to, at each of the multiple time steps, generate a final goal vector for the time step. The worker subsystem is configured to, at each of multiple time steps, use the final goal vector generated by the manager subsystem to generate a respective action score for each action in a predetermined set of actions.

公开(公告)号：US20200151515A1

公开(公告)日：2020-05-14

申请号：US16745757

申请日：2020-01-17

Applicant: DeepMind Technologies Limited

Inventor： Fabio Viola ,  Piotr Wojciech Mirowski ,  Andrea Banino ,  Razvan Pascanu ,  Hubert Josef Soyer ,  Andrew James Ballard ,  Sudarshan Kumaran ,  Raia Thais Hadsell ,  Laurent Sifre ,  Rostislav Goroshin ,  Koray Kavukcuoglu ,  Misha Man Ray Denil

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

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. In one aspect, a method of training an action selection policy neural network for use in selecting actions to be performed by an agent navigating through an environment to accomplish one or more goals comprises: receiving an observation image characterizing a current state of the environment; processing, using the action selection policy neural network, an input comprising the observation image to generate an action selection output; processing, using a geometry-prediction neural network, an intermediate output generated by the action selection policy neural network to predict a value of a feature of a geometry of the environment when in the current state; and backpropagating a gradient of a geometry-based auxiliary loss into the action selection policy neural network to determine a geometry-based auxiliary update for current values of the network parameters.

公开(公告)号：US10223617B1

公开(公告)日：2019-03-05

申请号：US14731348

申请日：2015-06-04

Applicant: DeepMind Technologies Limited

Inventor： Volodymyr Mnih ,  Koray Kavukcuoglu

IPC: G06K9/62 ,  G06K9/46 ,  G06K9/00 ,  G06K9/66

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using recurrent attention. One of the methods includes determining a location in the first image; extracting a glimpse from the first image using the location; generating a glimpse representation of the extracted glimpse; processing the glimpse representation using a recurrent neural network to update a current internal state of the recurrent neural network to generate a new internal state; processing the new internal state to select a location in a next image in the image sequence after the first image; and processing the new internal state to select an action from a predetermined set of possible actions.