公开(公告)号：US20220415453A1

公开(公告)日：2022-12-29

申请号：US17849269

申请日：2022-06-24

Applicant: DeepMind Technologies Limited

Inventor： Olaf Ronneberger ,  Marta Garnelo Abellanas ,  Dan Rosenbaum ,  Seyed Mohammadali Eslami ,  Jonas Anders Adler

IPC: G16C20/70 ,  G16C20/80

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media. One of the methods includes obtaining a plurality of images of a macromolecule having a plurality of atoms, training a decoder neural network on the plurality of images, and after the training, generating a plurality of conformations for at least a portion of the macromolecule that each include respective three-dimensional coordinates of each of the plurality of atoms, wherein generating each conformation includes sampling a conformation latent representation from a prior distribution over conformation latent representations, processing a respective input including the sampled conformation latent representation using the decoder neural network to generate a conformation output that specifies three-dimensional coordinates of each of the plurality of atoms for the conformation, and generating the conformation from the conformation output.

公开(公告)号：US20220374683A1

公开(公告)日：2022-11-24

申请号：US17668050

申请日：2022-02-09

Applicant: DeepMind Technologies Limited

Inventor： Thomas Edward Eccles ,  Ian Michael Gemp ,  János Kramár ,  Marta Garnelo Abellanas ,  Dan Rosenbaum ,  Yoram Bachrach ,  Thore Kurt Hartwig Graepel

IPC: G06N3/04 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting an optimal feature point in a continuous domain for a group of agents. A computer-implemented system obtains, for each of a plurality of agents, respective training data that comprises a respective utility score for each of a plurality of discrete points in the continuous domain. The system trains, for each of the plurality of agents and on the respective training data for the agents, a respective neural network that is configured to receive an input comprising a point in the continuous domain and to generate as output a predicted utility score for the agent at the point. And the system identifies the optimal point by optimizing an approximation of the shared outcome function that is defined by, for any given point in the continuous domain, a combination of the predicted utility scores generated by the respective neural networks for each of the plurality of agents by processing an input comprising the given point.

公开(公告)号：US20210097401A1

公开(公告)日：2021-04-01

申请号：US16968336

申请日：2019-02-11

Applicant: DeepMind Technologies Limited

Inventor： Tiago Miguel Sargento Pires Ramalho ,  Dan Rosenbaum ,  Marta Garnelo ,  Christopher Maddison ,  Seyed Mohammadali Eslami ,  Yee Whye Teh ,  Danilo Jimenez Rezende

IPC: G06N3/08 ,  G06N3/04 ,  A63F13/67

Abstract: According to a first aspect a network system to generate output data values from input data values according to one or In more learned data distributions comprises an input to receive a set of observations, each comprising a respective first data value for a first variable and a respective second data value for a second variable dependent upon the first variable. The system may comprise an encoder neural network system configured to encode each observation of the set of observations to provide an encoded output for each observation. The system may further comprise an aggregator configured to aggregate the encoded outputs for the set of observations and provide an aggregated output. The system may further comprise a decoder neural network system configured to receive a combination of the aggregated output and a target input value and to provide a decoder output. The target input value may comprise a value for the first variable and the decoder output may predict a corresponding value for the second variable.