公开(公告)号：US11836596B2

公开(公告)日：2023-12-05

申请号：US17107621

申请日：2020-11-30

Applicant: DeepMind Technologies Limited

Inventor： Mike Chrzanowski ,  Jack William Rae ,  Ryan Faulkner ,  Theophane Guillaume Weber ,  David Nunes Raposo ,  Adam Anthony Santoro

IPC: G06N3/08 ,  G06N3/042 ,  G06N3/04 ,  G06N20/00 ,  G06F18/2413

CPC classification number: G06N3/042 ,  G06F18/24137 ,  G06N3/04 ,  G06N3/08 ,  G06N20/00

Abstract: A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.

公开(公告)号：US20230124177A1

公开(公告)日：2023-04-20

申请号：US17914035

申请日：2021-06-04

Applicant: DeepMind Technologies Limited

Inventor： Siddhant Madhu Jayakumar ,  Razvan Pascanu ,  Jack William Rae ,  Simon Osindero ,  Erich Konrad Elsen

IPC: G06N3/08 ,  G06F18/211

Abstract: A computer-implemented method of training a neural network. The method comprises repeatedly determining a forward-pass set of network parameters by selecting a first sub-set of parameters of the neural network and setting all other parameters of the forward-pass set of network parameters to zero. The method then processes a training data item using the neural network in accordance with the forward-pass set of network parameters to generate a neural network output, determines a value of an objective function from the neural network output and the training data item, selects a second sub-set of network parameters, determines a backward-pass set of network parameters comprising the first and second sub-sets of parameters, and updates parameters corresponding to the backward-pass set of network parameters using a gradient estimate determined from the value of the objective function.

公开(公告)号：US12242947B2

公开(公告)日：2025-03-04

申请号：US16759561

申请日：2018-10-29

Applicant: DeepMind Technologies Limited

Inventor： Pablo Sprechmann ,  Siddhant Jayakumar ,  Jack William Rae ,  Alexander Pritzel ,  Adrià Puigdomènech Badia ,  Oriol Vinyals ,  Razvan Pascanu ,  Charles Blundell

IPC: G06N3/045 ,  G06N3/02 ,  G06N3/04 ,  G06N3/044 ,  G06N3/084

Abstract: There is described herein a computer-implemented method of processing an input data item. The method comprises processing the input data item using a parametric model to generate output data, wherein the parametric model comprises a first sub-model and a second sub-model. The processing comprises processing, by the first sub-model, the input data to generate a query data item, retrieving, from a memory storing data point-value pairs, at least one data point-value pair based upon the query data item and modifying weights of the second sub-model based upon the retrieved at least one data point-value pair. The output data is then generated based upon the modified second sub-model.

公开(公告)号：US20250053780A1

公开(公告)日：2025-02-13

申请号：US18662972

申请日：2024-05-13

Applicant: DeepMind Technologies Limited

Inventor： Jack William Rae ,  Timothy Paul Lillicrap ,  Sergey Bartunov

IPC: G06N3/045 ,  G06F16/22 ,  G06N3/08

Abstract: A system for compressed data storage using a neural network. The system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.

公开(公告)号：US12033055B2

公开(公告)日：2024-07-09

申请号：US17763984

申请日：2020-09-07

Applicant: DeepMind Technologies Limited

Inventor： Emilio Parisotto ,  Hasuk Song ,  Jack William Rae ,  Siddhant Madhu Jayakumar ,  Maxwell Elliot Jaderberg ,  Razvan Pascanu ,  Caglar Gulcehre

IPC: G06N3/044 ,  G06N3/048 ,  G06N3/08

CPC classification number: G06N3/044 ,  G06N3/048 ,  G06N3/08

Abstract: A system including an attention neural network that is configured to receive an input sequence and to process the input sequence to generate an output is described. The attention neural network includes: an attention block configured to receive a query input, a key input, and a value input that are derived from an attention block input. The attention block includes an attention neural network layer configured to: receive an attention layer input derived from the query input, the key input, and the value input, and apply an attention mechanism to the query input, the key input, and the value input to generate an attention layer output for the attention neural network layer; and a gating neural network layer configured to apply a gating mechanism to the attention block input and the attention layer output of the attention neural network layer to generate a gated attention output.

公开(公告)号：US20230061411A1

公开(公告)日：2023-03-02

申请号：US17410689

申请日：2021-08-24

Applicant: DeepMind Technologies Limited

Inventor： Tom Erez ,  Alexander Novikov ,  Emilio Parisotto ,  Jack William Rae ,  Konrad Zolna ,  Misha Man Ray Denil ,  Joao Ferdinando Gomes de Freitas ,  Oriol Vinyals ,  Scott Ellison Reed ,  Sergio Gomez ,  Ashley Deloris Edwards ,  Jacob Bruce ,  Gabriel Barth-Maron

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent to interact with an environment using an action selection neural network. In one aspect, a method comprises, at each time step in a sequence of time steps: generating a current representation of a state of a task being performed by the agent in the environment as of the current time step as a sequence of data elements; autoregressively generating a sequence of data elements representing a current action to be performed by the agent at the current time step; and after autoregressively generating the sequence of data elements representing the current action, causing the agent to perform the current action at the current time step.

公开(公告)号：US11151443B2

公开(公告)日：2021-10-19

申请号：US15424685

申请日：2017-02-03

Applicant: DeepMind Technologies Limited

Inventor： Ivo Danihelka ,  Gregory Duncan Wayne ,  Fu-min Wang ,  Edward Thomas Grefenstette ,  Jack William Rae ,  Alexander Benjamin Graves ,  Timothy Paul Lillicrap ,  Timothy James Alexander Harley ,  Jonathan James Hunt

IPC: G06N3/063 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a sparse memory access subsystem that is configured to perform operations comprising generating a sparse set of reading weights that includes a respective reading weight for each of the plurality of locations in the external memory using the read key, reading data from the plurality of locations in the external memory in accordance with the sparse set of reading weights, generating a set of writing weights that includes a respective writing weight for each of the plurality of locations in the external memory, and writing the write vector to the plurality of locations in the external memory in accordance with the writing weights.

公开(公告)号：US20210150314A1

公开(公告)日：2021-05-20

申请号：US17102318

申请日：2020-11-23

Applicant: DeepMind Technologies Limited

Inventor： Jack William Rae ,  Timothy Paul Lillicrap ,  Sergey Bartunov

IPC: G06N3/04 ,  G06F16/22 ,  G06N3/08

Abstract: A system for compressed data storage using a neural network. The system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.

公开(公告)号：US20210081795A1

公开(公告)日：2021-03-18

申请号：US17107621

申请日：2020-11-30

Applicant: DeepMind Technologies Limited

Inventor： Mike Chrzanowski ,  Jack William Rae ,  Ryan Faulkner ,  Theophane Guillaume Weber ,  David Nunes Raposo ,  Adam Anthony Santoro

IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04

Abstract: A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.

公开(公告)号：US10853725B2

公开(公告)日：2020-12-01

申请号：US16415954

申请日：2019-05-17

Applicant: DeepMind Technologies Limited

Inventor： Mike Chrzanowski ,  Jack William Rae ,  Ryan Faulkner ,  Theophane Guillaume Weber ,  David Nunes Raposo ,  Adam Anthony Santoro

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.