公开(公告)号：US20230124261A1

公开(公告)日：2023-04-20

申请号：US17914066

申请日：2021-05-12

Applicant: DeepMind Technologies Limited

Inventor： Benigno Uria-Martínez ,  Andrea Banino ,  Borja Ibarz Gabardos ,  Vinicius Zambaldi ,  Charles Blundell

IPC: G06N3/044 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a spatial embedding neural network that is configured to process data characterizing motion of an agent that is interacting with an environment to generate spatial embeddings. In one aspect, a method comprises: processing data characterizing the motion of the agent in the environment at the current time step using a spatial embedding neural network to generate a current spatial embedding for the current time step; determining a predicted score and a target score for each of a plurality of slots in an external memory, wherein each slot stores: (i) a representation of an observation characterizing a state of the environment, and (ii) a spatial embedding; and determining an update to values of the set of spatial embedding neural network parameters based on an error between the predicted scores and the target scores.

公开(公告)号：US20240256879A1

公开(公告)日：2024-08-01

申请号：US18423239

申请日：2024-01-25

Applicant: DeepMind Technologies Limited

Inventor： Beatrice Bevilacqua ,  Petar Velickovic ,  Jovana Mitrovic ,  Kyriacos Nikiforou ,  Ioana Bica ,  Borja Ibarz Gabardos

IPC: G06N3/0895

CPC classification number: G06N3/0895

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network to perform an algorithmic task. According to one aspect, there is provided a method comprising: obtaining an input dataset; generating a first augmented dataset and a second augmented dataset, wherein for both the first augmented dataset and the second augmented dataset: applying the computational algorithm to the augmented dataset causes the same computational operations to be performed at a target computational step as would be performed by applying the computational algorithm to the input dataset; processing the first augmented dataset and the second augmented dataset using the neural network, comprising, for each augmented dataset: generating an intermediate representation of the augmented dataset at an intermediate layer of the neural network; and training the neural network on an objective function, wherein the objective function comprises a self-supervised loss term.