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：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.