Deepmind Technologies Limited

Gdm Holding LLC

Charles Blundell

Oriol Vinyals

Alexander Pritzel

Meire Fortunato

Adrià Puigdomènech Badia

Bilal Piot

Razvan Pascanu

Daniel Pieter Wierstra

Remi Munos

Andrei-Alexandru Rusu

Julien Robert Michel Cornebise

Jacob Lee Menick

Benigno Uria-Martínez

Siddhant Jayakumar

Olivier Claude Pietquin

David Ha

Mohammad Gheshlaghi Azar

Chrisantha Thomas Fernando

Dylan Sunil Banarse

Yori Zwols

Pablo Sprechmann

Volodymyr Mnih

Jack William Rae

Andrea Banino

Matthew Botvinick

Adria Puigdomenech Badia

Zhaohan Guo

Mohammadamin Barekatain

Heiko Strathmann

Petar Velickovic

Olivier Tieleman

Steven James Kapturowski

Alex Vitvitskyi

Vinicius Zambaldi

Xiao Jing Wang

Samuel Ritter

Borja Ibarz Gabardos

Olivier Pietquin

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing persistent message passing using graph neural networks.

Persistent message passing for graph neural networks

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

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 selecting an action to be performed by a reinforcement learning agent. The method includes obtaining an observation characterizing a current state of an environment. For each layer parameter of each noisy layer of a neural network, a respective noise value is determined. For each layer parameter of each noisy layer, a noisy current value for the layer parameter is determined from a current value of the layer parameter, a current value of a corresponding noise parameter, and the noise value. A network input including the observation is processed using the neural network in accordance with the noisy current values to generate a network output for the network input. An action is selected from a set of possible actions to be performed by the agent in response to the observation using the network output.

Noisy neural network layers with noise parameters

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network. In one aspect, a method includes maintaining data specifying, for each of the network parameters, current values of a respective set of distribution parameters that define a posterior distribution over possible values for the network parameter. A respective current training value for each of the network parameters is determined from a respective temporary gradient value for the network parameter. The current values of the respective sets of distribution parameters for the network parameters are updated in accordance with the respective current training values for the network parameters. The trained values of the network parameters are determined based on the updated current values of the respective sets of distribution parameters.

Training neural networks using posterior sharpening

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using multi-task neural networks. One of the methods includes receiving a first network input and data identifying a first machine learning task to be performed on the first network input; selecting a path through the plurality of layers in a super neural network that is specific to the first machine learning task, the path specifying, for each of the layers, a proper subset of the modular neural networks in the layer that are designated as active when performing the first machine learning task; and causing the super neural network to process the first network input using (i) for each layer, the modular neural networks in the layer that are designated as active by the selected path and (ii) the set of one or more output layers corresponding to the identified first machine learning task.

Multi-task neural networks with task-specific paths

A method includes maintaining respective episodic memory data for each of multiple actions; receiving a current observation characterizing a current state of an environment being interacted with by an agent; processing the current observation using an embedding neural network in accordance with current values of parameters of the embedding neural network to generate a current key embedding for the current observation; for each action of the plurality of actions: determining the p nearest key embeddings in the episodic memory data for the action to the current key embedding according to a distance measure, and determining a Q value for the action from the return estimates mapped to by the p nearest key embeddings in the episodic memory data for the action; and selecting, using the Q values for the actions, an action from the multiple actions as the action to be performed by the agent.

Neural episodic control

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network that is used to select actions to be performed by an agent interacting with an environment. In one aspect, the method comprises: receiving an observation characterizing a current state of the environment; processing the observation and an exploration importance factor using the action selection neural network to generate an action selection output; selecting an action to be performed by the agent using the action selection output; determining an exploration reward; determining an overall reward based on: (i) the exploration importance factor, and (ii) the exploration reward; and training the action selection neural network using a reinforcement learning technique based on the overall reward.

Jointly learning exploratory and non-exploratory action selection policies

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for content recommendation using neural networks. In One aspect, a method includes: receiving context information for an action recommendation from multiple possible actions; processing the context information using a neural network that includes Bayesian neural network layers to generate, for each of the actions, one or more parameters of a distribution over possible action scores for the action, where each parameter for each Bayesian layer is associated with data representing a probability distribution over multiple possible current values for the parameter; for each parameter of each Bayesian neural network layer, selecting the current value for the parameter using data representing probability distribution over possible current values for the parameter; and selecting an action from multiple possible actions using the parameters of the distributions over the possible action scores for the action.

Recommending content using neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a system output using a remembered value of a neural network hidden state. In one aspect, a system comprises an external memory that maintains context experience tuples respectively comprising: (i) a key embedding of context data, and (ii) a value of a hidden state of a neural network at the respective previous time step. The neural network is configured to receive a system input and a remembered value of the hidden state of the neural network and to generate a system output. The system comprises a memory interface subsystem that is configured to determine a key embedding for current context data, determine a remembered value of the hidden state of the neural network based on the key embedding, and provide the remembered value of the hidden state as an input to the neural network.

Selecting actions by reverting to previous learned action selection policies

Growing community of inventors

London, United Kingdom

Charles Blundell