公开(公告)号：US12271823B2

公开(公告)日：2025-04-08

申请号：US18180754

申请日：2023-03-08

Applicant: DeepMind Technologies Limited

Inventor： Misha Man Ray Denil ,  Tom Schaul ,  Marcin Andrychowicz ,  Joao Ferdinando Gomes de Freitas ,  Sergio Gomez Colmenarejo ,  Matthew William Hoffman ,  David Benjamin Pfau

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

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for training machine learning models. One method includes obtaining a machine learning model, wherein the machine learning model comprises one or more model parameters, and the machine learning model is trained using gradient descent techniques to optimize an objective function; determining an update rule for the model parameters using a recurrent neural network (RNN); and applying a determined update rule for a final time step in a sequence of multiple time steps to the model parameters.

公开(公告)号：US20230376771A1

公开(公告)日：2023-11-23

申请号：US18180754

申请日：2023-03-08

Applicant: DeepMind Technologies Limited

Inventor： Misha Man Ray Denil ,  Tom Schaul ,  Marcin Andrychowicz ,  Joao Ferdinando Gomes de Freitas ,  Sergio Gomez Colmenarejo ,  Matthew William Hoffman ,  David Benjamin Pfau

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

CPC classification number: G06N3/084 ,  G06N3/044 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for training machine learning models. One method includes obtaining a machine learning model, wherein the machine learning model comprises one or more model parameters, and the machine learning model is trained using gradient descent techniques to optimize an objective function; determining an update rule for the model parameters using a recurrent neural network (RNN); and applying a determined update rule for a final time step in a sequence of multiple time steps to the model parameters.

公开(公告)号：US20210064961A1

公开(公告)日：2021-03-04

申请号：US17011569

申请日：2020-09-03

Applicant: DeepMind Technologies Limited

Inventor： David Benjamin Pfau ,  James Spencer ,  Alexander Graeme de Garis Matthews

IPC: G06N3/04 ,  G06F17/18

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using antisymmetric neural networks.

公开(公告)号：US12248861B2

公开(公告)日：2025-03-11

申请号：US17011569

申请日：2020-09-03

Applicant: DeepMind Technologies Limited

Inventor： David Benjamin Pfau ,  James Spencer ,  Alexander Graeme de Garis Matthews

IPC: G06N3/04 ,  G06F17/18

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using antisymmetric neural networks.

公开(公告)号：US11615310B2

公开(公告)日：2023-03-28

申请号：US16302592

申请日：2017-05-19

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： Misha Man Ray Denil ,  Tom Schaul ,  Marcin Andrychowicz ,  Joao Ferdinando Gomes de Freitas ,  Sergio Gomez Colmenarejo ,  Matthew William Hoffman ,  David Benjamin Pfau

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for training machine learning models. One method includes obtaining a machine learning model, wherein the machine learning model comprises one or more model parameters, and the machine learning model is trained using gradient descent techniques to optimize an objective function; determining an update rule for the model parameters using a recurrent neural network (RNN); and applying a determined update rule for a final time step in a sequence of multiple time steps to the model parameters.

公开(公告)号：US20210166131A1

公开(公告)日：2021-06-03

申请号：US16972491

申请日：2019-06-06

Applicant: DeepMind Technologies Limited

Inventor： David Benjamin Pfau ,  Stig Petersen ,  Ashish Agarwal ,  David Barrett ,  Kimberly Stachenfeld

IPC: G06N3/08 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network having a plurality of network parameters and being configured to process an input data item to generate a feature representation comprising a values for each of a plurality of features of the input data item.