Deepmind Technologies Limited

Google Inc.

Oriol Vinyals

Aaron Gerard Antonius Van Den Oord

Navdeep Jaitly

Quoc V Le

Karen Simonyan

Sander Etienne Lea Dieleman

Noam M Shazeer

Samy Bengio

Ilya Sutskever

Nal Emmerich Kalchbrenner

Yujia Li

Charles Blundell

Lukasz Mieczyslaw Kaiser

Samuel Bengio

Scott Ellison Reed

Jeffrey Adgate Dean

William Chan

Geoffrey Everest Hinton

Alexander Toshev

Razvan Pascanu

Joao Ferdinando Gomes De Freitas

Danilo Jimenez Rezende

Dumitru Erhan

Koray Kavukcuoglu

Nicolas Manfred Otto Heess

Maxwell Elliot Jaderberg

Daniel Pieter Wierstra

Adrià Puigdomènech Badia

Tara N Sainath

Jakob David Uszkoreit

Hasim Sak

George Dan Toderici

David Silver

Sudheendra Vijayanarasimhan

Thomas Chadwick Walters

Sze Chie Lim

Chenjie Gu

Rajat Monga

Andrew William Senior

Vincent Olivier Vanhoucke

Johan Schalkwyk

Larry Paul Heck

Brian Strope

Alexander Benjamin Graves

Maria Carolina Parada San Martin

Patrick An Phu Nguyen

Thomas L Dean

Jack William Rae

Wojciech Czarnecki

Andrew Zisserman

Enrique Alfonseca

Howard Scott Roy

Joao Carreira

Yutian Chen

Yazhe Li

Lasse Espeholt

Theophane Guillaume Weber

Peter William Battaglia

Sebastien Henri Andre Racaniere

David Paul Reichert

Lars Buesing

Alejandro Luebs

Mostafa Dehghani

Ioannis Alexandros Assael

Brendan Shillingford

Christopher James Dyer

Thomas Dullien

Wojciech Zaremba

Stephan Gouws

Meire Fortunato

Arthur Clement Guez

Pushmeet Kohli

Minh-Thang Luong

Benjamin Poole

Ali Razavi-Nematollahi

Cristina Garbacea

Heiga Zen

Yue Hei Ng

Matthew John Hausknecht

Simon Osindero

David Budden

Alexander Pritzel

Ziyu Wang

Sergio Gomez Colmenarejo

Hanxiao Liu

Siddhant Jayakumar

Yusuf Aytar

Andrew W Senior

Ekaterina Filippova

Chrisantha Thomas Fernando

Alexander Novikov

Shalini Ghosh

Pablo Sprechmann

Carl Doersch

Fengning Ding

Adria Puigdomenech Badia

Catalin-Dumitru Ionescu

Carlos Alberto Colmenares Rojas

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

There is described herein a computer-implemented method of processing an input data item. The method comprises processing the input data item using a parametric model to generate output data, wherein the parametric model comprises a first sub-model and a second sub-model. The processing comprises processing, by the first sub-model, the input data to generate a query data item, retrieving, from a memory storing data point-value pairs, at least one data point-value pair based upon the query data item and modifying weights of the second sub-model based upon the retrieved at least one data point-value pair. The output data is then generated based upon the modified second sub-model.

Machine learning systems with memory based parameter adaptation for learning fast and slower

There is described a neural network system for generating a graph, the graph comprising a set of nodes and edges. The system comprises one or more neural networks configured to represent a probability distribution over sequences of node generating decisions and/or edge generating decisions, and one or more computers configured to sample the probability distribution represented by the one or more neural networks to generate a graph.

Graph neural network systems for generating structured representations of objects

Methods, systems, and apparatus for classifying a new example using a comparison set of comparison examples. One method includes maintaining a comparison set, the comparison set including comparison examples and a respective label vector for each of the comparison examples, each label vector including a respective score for each label in a predetermined set of labels; receiving a new example; determining a respective attention weight for each comparison example by applying a neural network attention mechanism to the new example and to the comparison examples; and generating a respective label score for each label in the predetermined set of labels from, for each of the comparison examples, the respective attention weight for the comparison example and the respective label vector for the comparison example, in which the respective label score for each of the labels represents a likelihood that the label is a correct label for the new example.

Classifying input examples using a comparison set

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network having a plurality of policy parameters and used to select actions to be performed by an agent to control the agent to perform a particular task while interacting with one or more other agents in an environment. In one aspect, the method includes: maintaining data specifying a pool of candidate action selection policies; maintaining data specifying respective matchmaking policy; and training the policy neural network using a reinforcement learning technique to update the policy parameters. The policy parameters define policies to be used in controlling the agent to perform the particular task.

Multi-agent reinforcement learning with matchmaking policies

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating descriptions of input images. One of the methods includes obtaining an input image; processing the input image using a first neural network to generate an alternative representation for the input image; and processing the alternative representation for the input image using a second neural network to generate a sequence of a plurality of words in a target natural language that describes the input image.

Generating natural language descriptions of images

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network that is configured to process an input observation to generate a latent representation of the input observation. In one aspect, a method includes: obtaining a sequence of observations; for each observation in the sequence of observations, processing the observation using the encoder neural network to generate a latent representation of the observation; for each of one or more given observations in the sequence of observations: generating a context latent representation of the given observation; and generating, from the context latent representation of the given observation, a respective estimate of the latent representations of one or more particular observations that are after the given observation in the sequence of observations.

Learning observation representations by predicting the future in latent space

There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.

Deep neural network system for similarity-based graph representations

This document generally describes a neural network training system, including one or more computers, that trains a recurrent neural network (RNN) to receive an input, e.g., an input sequence, and to generate a sequence of outputs from the input sequence. In some implementations, training can include, for each position after an initial position in a training target sequence, selecting a preceding output of the RNN to provide as input to the RNN at the position, including determining whether to select as the preceding output (i) a true output in a preceding position in the output order or (ii) a value derived from an output of the RNN for the preceding position in an output order generated in accordance with current values of the parameters of the recurrent neural network.

Training recurrent neural networks to generate sequences

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input data items. One of the methods includes receiving an input data item; providing the input data item as input to an encoder neural network to obtain an encoder output for the input data item; and generating a discrete latent representation of the input data item from the encoder output, comprising: for each of the latent variables, determining, from a set of latent embedding vectors in the memory, a latent embedding vector that is nearest to the encoded vector for the latent variable.

Generating discrete latent representations of input data items

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing sequences using convolutional neural networks. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.

Processing sequences using convolutional neural networks

A feedforward generative neural network that generates an output example that includes multiple output samples of a particular type in a single neural network inference. Optionally, the generation may be conditioned on a context input. For example, the feedforward generative neural network may generate a speech waveform that is a verbalization of an input text segment conditioned on linguistic features of the text segment.

Feedforward generative neural networks

A computer-implemented method for automatically determining a neural network architecture represents a neural network architecture as a data structure defining a hierarchical set of directed acyclic graphs in multiple levels. Each graph has an input, an output, and a plurality of nodes between the input and the output. At each level, a corresponding set of the nodes are connected pairwise by directed edges which indicate operations performed on outputs of one node to generate an input to another node. Each level is associated with a corresponding set of operations. At a lowest level, the operations associated with each edge are selected from a set of primitive operations. The method includes repeatedly generating new sample neural network architectures, and evaluating their fitness. The modification is performed by selecting a level, selecting two nodes at that level, and modifying, removing or adding an edge between those nodes according to operations associated with lower levels of the hierarchy.

Using hierarchical representations for neural network architecture searching

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a distilled machine learning model. One of the methods includes training a cumbersome machine learning model, wherein the cumbersome machine learning model is configured to receive an input and generate a respective score for each of a plurality of classes; and training a distilled machine learning model on a plurality of training inputs, wherein the distilled machine learning model is also configured to receive inputs and generate scores for the plurality of classes, comprising: processing each training input using the cumbersome machine learning model to generate a cumbersome target soft output for the training input; and training the distilled machine learning model to, for each of the training inputs, generate a soft output that matches the cumbersome target soft output for the training input.

Training distilled machine learning models

Growing community of inventors

London, United Kingdom

Oriol Vinyals