公开(公告)号：US11210579B2

公开(公告)日：2021-12-28

申请号：US16831566

申请日：2020-03-26

Applicant: DeepMind Technologies Limited

Inventor： Alexander Benjamin Graves ,  Ivo Danihelka ,  Gregory Duncan Wayne

IPC: 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 methods includes providing an output derived from a first portion of a neural network output as a system output; determining one or more sets of writing weights for each of a plurality of locations in an external memory; writing data defined by a third portion of the neural network output to the external memory in accordance with the sets of writing weights; determining one or more sets of reading weights for each of the plurality of locations in the external memory from a fourth portion of the neural network output; reading data from the external memory in accordance with the sets of reading weights; and combining the data read from the external memory with a next system input to generate the next neural network input.

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：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

IPC: G06N3/08 ,  G06N3/04

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：US10650302B2

公开(公告)日：2020-05-12

申请号：US14885086

申请日：2015-10-16

Applicant: DeepMind Technologies Limited

Inventor： Alexander Benjamin Graves ,  Ivo Danihelka ,  Gregory Duncan Wayne

IPC: 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 methods includes providing an output derived from a first portion of a neural network output as a system output; determining one or more sets of writing weights for each of a plurality of locations in an external memory; writing data defined by a third portion of the neural network output to the external memory in accordance with the sets of writing weights; determining one or more sets of reading weights for each of the plurality of locations in the external memory from a fourth portion of the neural network output; reading data from the external memory in accordance with the sets of reading weights; and combining the data read from the external memory with a next system input to generate the next neural network input.

公开(公告)号：US12299575B2

公开(公告)日：2025-05-13

申请号：US17093373

申请日：2020-11-09

Applicant: DeepMind Technologies Limited

Inventor： Alexander Benjamin Graves ,  Ivo Danihelka ,  Timothy James Alexander Harley ,  Malcolm Kevin Campbell Reynolds ,  Gregory Duncan Wayne

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/044 ,  G06N3/082 ,  G06N3/063

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 memory interface subsystem that is configured to perform operations comprising determining a respective content-based weight for each of a plurality of locations in an external memory; determining a respective allocation weight for each of the plurality of locations in the external memory; determining a respective final writing weight for each of the plurality of locations in the external memory from the respective content-based weight for the location and the respective allocation weight for the location; and writing data defined by the write vector to the external memory in accordance with the final writing weights.

公开(公告)号：US11080587B2

公开(公告)日：2021-08-03

申请号：US15016160

申请日：2016-02-04

Applicant: DeepMind Technologies Limited

Inventor： Karol Gregor ,  Ivo Danihelka

IPC: G06N3/04 ,  G10L25/30 ,  G10L13/02

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating data items. A method includes reading a glimpse from a data item using a decoder hidden state vector of a decoder for a preceding time step, providing, as input to a encoder, the glimpse and decoder hidden state vector for the preceding time step for processing, receiving, as output from the encoder, a generated encoder hidden state vector for the time step, generating a decoder input from the generated encoder hidden state vector, providing the decoder input to the decoder for processing, receiving, as output from the decoder, a generated a decoder hidden state vector for the time step, generating a neural network output update from the decoder hidden state vector for the time step, and combining the neural network output update with a current neural network output to generate an updated neural network output.

公开(公告)号：US10482373B1

公开(公告)日：2019-11-19

申请号：US15174806

申请日：2016-06-06

Applicant: DeepMind Technologies Limited

Inventor： Nal Emmerich Kalchbrenner ,  Ivo Danihelka ,  Alexander Benjamin Graves

IPC: G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing grid Long Short-Term Memory (LSTM) neural networks that includes a plurality of N-LSTM blocks arranged in an N-dimensional grid. Each N-LSTM block is configured to: receive N input hidden vectors, the N input hidden vectors each corresponding to a respective one of the N dimensions; receive N input memory vectors, the N input memory vectors each corresponding to a respective one of the N dimensions; and, for each of the dimensions, apply a respective transform for the dimension to the memory hidden vector corresponding to the dimension and the input hidden vector corresponding to the dimension to generate a new hidden vector corresponding to the dimension and a new memory vector corresponding to the dimension.

公开(公告)号：US11256990B2

公开(公告)日：2022-02-22

申请号：US16303101

申请日：2017-05-19

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： Marc Lanctot ,  Audrunas Gruslys ,  Ivo Danihelka ,  Remi Munos

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a recurrent neural network on training sequences using backpropagation through time. In one aspect, a method includes receiving a training sequence including a respective input at each of a number of time steps; obtaining data defining an amount of memory allocated to storing forward propagation information for use during backpropagation; determining, from the number of time steps in the training sequence and from the amount of memory allocated to storing the forward propagation information, a training policy for processing the training sequence, wherein the training policy defines when to store forward propagation information during forward propagation of the training sequence; and training the recurrent neural network on the training sequence in accordance with the training policy.

公开(公告)号：US20210350207A1

公开(公告)日：2021-11-11

申请号：US17384280

申请日：2021-07-23

Applicant: DeepMind Technologies Limited

Inventor： Karol Gregor ,  Ivo Danihelka

IPC: G06N3/04

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating data items. A method includes reading a glimpse from a data item using a decoder hidden state vector of a decoder for a preceding time step, providing, as input to a encoder, the glimpse and decoder hidden state vector for the preceding time step for processing, receiving, as output from the encoder, a generated encoder hidden state vector for the time step, generating a decoder input from the generated encoder hidden state vector, providing the decoder input to the decoder for processing, receiving, as output from the decoder, a generated a decoder hidden state vector for the time step, generating a neural network output update from the decoder hidden state vector for the time step, and combining the neural network output update with a current neural network output to generate an updated neural network output.

公开(公告)号：US11080594B2

公开(公告)日：2021-08-03

申请号：US15396331

申请日：2016-12-30

Applicant: DeepMind Technologies Limited

Inventor： Ilya Sutskever ,  Ivo Danihelka ,  Alexander Benjamin Graves ,  Gregory Duncan Wayne ,  Wojciech Zaremba

IPC: G06N3/08 ,  G06F3/06 ,  G06N3/04 ,  G06N3/063

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory using reinforcement learning. One of the methods includes providing an output derived from the system output portion of the neural network output as a system output in the sequence of system outputs; selecting a memory access process from a predetermined set of memory access processes for accessing the external memory from the reinforcement learning portion of the neural network output; writing and reading data from locations in the external memory in accordance with the selected memory access process using the differentiable portion of the neural network output; and combining the data read from the external memory with a next system input in the sequence of system inputs to generate a next neural network input in the sequence of neural network inputs.