公开(公告)号：US20250103856A1

公开(公告)日：2025-03-27

申请号：US18832817

申请日：2023-01-30

Applicant: DeepMind Technologies Limited

Inventor： Joao Carreira ,  Andrew Coulter Jaegle ,  Skanda Kumar Koppula ,  Daniel Zoran ,  Adrià Recasens Continente ,  Catalin-Dumitru Ionescu ,  Olivier Jean Hénaff ,  Evan Gerard Shelhamer ,  Relja Arandjelovic ,  Matthew Botvinick ,  Oriol Vinyals ,  Karen Simonyan ,  Andrew Zisserman

IPC: G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using a neural network to generate a network output that characterizes an entity. In one aspect, a method includes: obtaining a representation of the entity as a set of data element embeddings, obtaining a set of latent embeddings, and processing: (i) the set of data element embeddings, and (ii) the set of latent embeddings, using the neural network to generate the network output. The neural network includes a sequence of neural network blocks including: (i) one or more local cross-attention blocks, and (ii) an output block. Each local cross-attention block partitions the set of latent embeddings and the set of data element embeddings into proper subsets, and updates each proper subset of the set of latent embeddings using attention over only the corresponding proper subset of the set of data element embeddings.

公开(公告)号：US20240386281A1

公开(公告)日：2024-11-21

申请号：US18668080

申请日：2024-05-17

Applicant: DeepMind Technologies Limited

Inventor： Daniel Zoran ,  Wilka Torrico Carvahlo ,  Angelos Filos ,  Danilo Jimenez Rezende

IPC: G06N3/096

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium. for controlling agents by transferring successor features to new tasks.

公开(公告)号：US20240221362A1

公开(公告)日：2024-07-04

申请号：US18289171

申请日：2022-05-27

Applicant: DeepMind Technologies Limited

Inventor： Rishabh Kabra ,  Daniel Zoran ,  Goker Erdogan ,  Antonia Phoebe Nina Creswell ,  Loic Matthey-de-l'Endroit ,  Matthew Botvinick ,  Alexander Lerchner ,  Christopher Paul Burgess

IPC: G06V10/771 ,  G06T9/00 ,  G06V10/44 ,  G06V10/82

CPC classification number: G06V10/771 ,  G06T9/00 ,  G06V10/44 ,  G06V10/82

Abstract: A computer-implemented video generation neural network system, configured to determine a value for each of a set of object latent variables by sampling from a respective prior object latent distribution for the object latent variable. The system comprises a trained image frame decoder neural network configured to, for each pixel of each generated image frame and for each generated image frame time step process determined values of the object latent variables to determine parameters of a pixel distribution for each of the object latent variables, combine the pixel distributions for each of the object latent variables to determine a combined pixel distribution, and sample from the combined pixel distribution to determine a value for the pixel and for the time step.

公开(公告)号：US20240070972A1

公开(公告)日：2024-02-29

申请号：US18275332

申请日：2022-02-04

Applicant: DeepMind Technologies Limited

Inventor： Adam Roman Kosiorek ,  Heiko Strathmann ,  Danilo Jimenez Rezende ,  Daniel Zoran ,  Pol Moreno Comellas

IPC: G06T15/20 ,  G06N3/045 ,  G06N3/084 ,  G06T15/06 ,  G06T15/50

CPC classification number: G06T15/20 ,  G06N3/045 ,  G06N3/084 ,  G06T15/06 ,  G06T15/506

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for rendering a new image that depicts a scene from a perspective of a camera at a new camera location. In one aspect, a method comprises: receiving a plurality of observations characterizing the scene; generating a latent variable representing the scene from the plurality of observations characterizing the scene; conditioning a scene representation neural network on the latent variable representing the scene, wherein the scene representation neural network conditioned on the latent variable representing the scene defines a geometric model of the scene as a three-dimensional (3D) radiance field; and rendering the new image that depicts the scene from the perspective of the camera at the new camera location using the scene representation neural network conditioned on the latent variable representing the scene.

公开(公告)号：US20240232580A1

公开(公告)日：2024-07-11

申请号：US18284595

申请日：2022-05-27

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： Andrew Coulter Jaegle ,  Jean-Baptiste Alayrac ,  Sebastian Borgeaud Dit Avocat ,  Catalin-Dumitru Ionescu ,  Carl Doersch ,  Fengning Ding ,  Oriol Vinyals ,  Olivier Jean Hénaff ,  Skanda Kumar Koppula ,  Daniel Zoran ,  Andrew Brock ,  Evan Gerard Shelhamer ,  Andrew Zisserman ,  Joao Carreira

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a network output using a neural network. In one aspect, a method comprises: obtaining: (i) a network input to a neural network, and (ii) a set of query embeddings; processing the network input using the neural network to generate a network output that comprises a respective dimension corresponding to each query embedding in the set of query embeddings, comprising: processing the network input using an encoder block of the neural network to generate a representation of the network input as a set of latent embeddings; and processing: (i) the set of latent embeddings, and (ii) the set of query embeddings, using a cross-attention block that generates each dimension of the network output by cross-attention of a corresponding query embedding over the set of latent embeddings.