Deepmind Technologies Limited

Google Inc.

Shakir Mohamed

Xavier Glorot

Ivo Danihelka

Danilo Jimenez Rezende

Daniel Pieter Wierstra

Alexander Lerchner

Sebastien Henri Andre Racaniere

Loic Matthey-de-l'Endroit

Irina Higgins

Arka Tilak Pal

Silvia Chiappa

Jack William Rae

Trevor Back

Harry Askham

Joseph R Ledsam

Nenad Tomasev

Clemens Ludwig Meyer

Suman Ravuri

Ivan Protsyuk

Michal Zielinski

Anne Mottram

Andre Saraiva Nobre Dos Santos

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting future adverse health events using neural networks. One of the methods includes receiving electronic health record data for a patient; generating, from the electronic health record data, an input sequence comprising a respective feature representation at each of a plurality of time window time steps, comprising, for each time window time step: determining, for each of the possible numerical features, whether the numerical feature occurred during the time window; and generating, for each of the possible numerical features, one or more presence features that identify whether the numerical feature occurred during the time window; and processing the input sequence using a neural network to generate a neural network output that characterizes a predicted likelihood that an adverse health event will occur to the patient.

Prediction of future adverse health events using neural networks by pre-processing input sequences to include presence features

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

Recurrent environment predictors

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

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a variational auto-encoder (VAE) to generate disentangled latent factors on unlabeled training images. In one aspect, a method includes receiving the plurality of unlabeled training images, and, for each unlabeled training image, processing the unlabeled training image using the VAE to determine the latent representation of the unlabeled training image and to generate a reconstruction of the unlabeled training image in accordance with current values of the parameters of the VAE, and adjusting current values of the parameters of the VAE by optimizing a loss function that depends on a quality of the reconstruction and also on a degree of independence between the latent factors in the latent representation of the unlabeled training image.

Training variational autoencoders to generate disentangled latent factors

Growing community of inventors

London, United Kingdom

Shakir Mohamed