Deepmind Technologies Limited

Google Inc.

Gdm Holding LLC

Danilo Jimenez Rezende

Oriol Vinyals

Seyed Mohammadali Eslami

Aaron Gerard Antonius Van Den Oord

Razvan Pascanu

Nicolas Manfred Otto Heess

Joao Ferdinando Gomes De Freitas

Ivo Danihelka

Scott Ellison Reed

Daniel Pieter Wierstra

Yujia Li

Adrià Puigdomènech Badia

Karol Gregor

Shakir Mohamed

Theophane Guillaume Weber

Yutian Chen

Peter William Battaglia

Sebastien Henri Andre Racaniere

Arthur Clement Guez

Frederic Olivier Besse

Andriy Mnih

Lars Buesing

David Paul Reichert

Andrew Zisserman

Olaf Ronneberger

Bernardino Romera-Paredes

Julien Robert Michel Cornebise

Pushmeet Kohli

Daniel Zorn

Simon Kohl

Jorg Bornschein

Daniël Pieter Wierstra

Georgios Papamakarios

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for image rendering. In one aspect, a method comprises receiving a plurality of observations characterizing a particular scene, each observation comprising an image of the particular scene and data identifying a location of a camera that captured the image. In another aspect, the method comprises receiving a plurality of observations characterizing a particular video, each observation comprising a video frame from the particular video and data identifying a time stamp of the video frame in the particular video. In yet another aspect, the method comprises receiving a plurality of observations characterizing a particular image, each observation comprising a crop of the particular image and data characterizing the crop of the particular image. The method processes each of the plurality of observations using an observation neural network to determine a numeric representation as output.

Scene understanding and generation using neural networks

A system comprising a causal convolutional neural network to autoregressively generate a succession of values of a data item conditioned upon previously generated values of the data item. The system includes support memory for a set of support data patches each of which comprises an encoding of an example data item. A soft attention mechanism attends to one or more patches when generating the current item value. The soft attention mechanism determines a set of scores for the support data patches, for example in the form of a soft attention query vector dependent upon the previously generated values of the data item. The soft attention query vector is used to query the memory. When generating the value of the data item at a current iteration layers of the causal convolutional neural network are conditioned upon the support data patches weighted by the scores.

Auto-regressive neural network systems with a soft attention mechanism using support data patches

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a plurality of possible segmentations of an image. In one aspect, a method comprises: receiving a request to generate a plurality of possible segmentations of an image; sampling a plurality of latent variables from a latent space, wherein each latent variable is sampled from the latent space in accordance with a respective probability distribution over the latent space that is determined based on the image; generating a plurality of possible segmentations of the image, comprising, for each latent variable, processing the image and the latent variable using a segmentation neural network having a plurality of segmentation neural network parameters to generate the possible segmentation of the image; and providing the plurality of possible segmentations of the image in response to the request.

Sampling latent variables to generate multiple segmentations of an image

A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.

Imagination-based agent neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model. One of the methods includes, for each training observation: determining a plurality of latent variable value configurations, each latent variable value configuration being a combination of latent variable values that includes a respective value for each of the latent variables; determining, for each of the plurality of latent variable value configurations, a respective local learning signal that is minimally dependent on each of the other latent variable value configurations in the plurality of latent variable value configurations; determining an unbiased estimate of a gradient of the objective function using the local learning signals; and updating current values of the parameters of the machine learning model using the unbiased estimate of the gradient.

Training latent variable machine learning models using multi-sample objectives

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating data items. One of the systems is a neural network system comprising a memory storing a plurality of template data items; one or more processors configured to select a memory address based upon a received input data item, and retrieve a template data item from the memory based upon the selected memory address; an encoder neural network configured to process the received input data item and the retrieved template data item to generate a latent variable representation; and a decoder neural network configured to process the retrieved template data item and the latent variable representation to generate an output data item.

Generating output data items using template data items

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network system. In one aspect, a neural network system includes a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the latent variables to update a hidden state of the recurrent neural network; and a generative subsystem that is configured to, for each time step, generate the set of latent variables for the time step and provide the set of latent variables as input to the recurrent neural network; update a hidden canvas using the updated hidden state of the recurrent neural network; and, for a last time step, generate an output image using the updated hidden canvas for the last time step.

Generative neural networks

We describe a signal processor, the signal processor comprising: a probability vector generation system, wherein said probability vector generation system has an input to receive a category vector for a category of output example and an output to provide a probability vector for said category of output example, wherein said output example comprises a set of data points, and wherein said probability vector defines a probability of each of said set of data points for said category of output example; a memory storing a plurality of said category vectors, one for each of a plurality of said categories of output example; and a stochastic selector to select a said stored category of output example for presentation of the corresponding category vector to said probability vector generation system; wherein said signal processor is configured to output data for an output example corresponding to said selected stored category.

Signal processing systems

Growing community of inventors

London, United Kingdom

Danilo Jimenez Rezende