Search Results for author:
Found 56 papers, 28 papers with code
Modelling Genetic Variations using Fragmentation-Coagulation Processes
We propose a novel class of Bayesian nonparametric models for sequential data called fragmentation-coagulation processes (FCPs).
Modelling Reciprocating Relationships with Hawkes Processes
We present a Bayesian nonparametric model that discovers implicit social structure from interaction time-series data.
Deep AutoRegressive Networks
We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data.
Bayesian Hierarchical Community Discovery
We propose an efficient Bayesian nonparametric model for discovering hierarchical community structure in social networks.
The Bayesian Echo Chamber: Modeling Social Influence via Linguistic Accommodation
We present the Bayesian Echo Chamber, a new Bayesian generative model for social interaction data.
Weight Uncertainty in Neural Networks
We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop.
Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server
The posterior server allows scalable and robust Bayesian learning in cases where a data set is stored in a distributed manner across a cluster, with each compute node containing a disjoint subset of data.
Deep Exploration via Bootstrapped DQN
Efficient exploration in complex environments remains a major challenge for reinforcement learning.
Ranked #6 on
Atari Games
on Atari 2600 Breakout
Matching Networks for One Shot Learning
Our algorithm improves one-shot accuracy on ImageNet from 87. 6% to 93. 2% and from 88. 0% to 93. 8% on Omniglot compared to competing approaches.
Model-Free Episodic Control
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance.
Early Visual Concept Learning with Unsupervised Deep Learning
Automated discovery of early visual concepts from raw image data is a major open challenge in AI research.
Learning to reinforcement learn
We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks.
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks.
Ranked #5 on
Continual Learning
on F-CelebA (10 tasks)
Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees
We introduce a new method called differentiable boundary tree which allows for learning deep kNN representations.
Neural Episodic Control
Deep reinforcement learning methods attain super-human performance in a wide range of environments.
Bayesian Recurrent Neural Networks
We also empirically demonstrate how Bayesian RNNs are superior to traditional RNNs on a language modelling benchmark and an image captioning task, as well as showing how each of these methods improve our model over a variety of other schemes for training them.
Noisy Networks for Exploration
We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration.
Ranked #1 on
Atari Games
on Atari 2600 Surround
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Domain adaptation is an important open problem in deep reinforcement learning (RL).
Revisiting Bayes by Backprop
We also empirically demonstrate how Bayesian RNNs are superior to traditional RNNs on a language modelling benchmark and an image captioning task, as well as showing how each of these methods improve our model over a variety of other schemes for training them.
Memory-based Parameter Adaptation
Deep neural networks have excelled on a wide range of problems, from vision to language and game playing.
Pushing the bounds of dropout
We show that dropout training is best understood as performing MAP estimation concurrently for a family of conditional models whose objectives are themselves lower bounded by the original dropout objective.
Ranked #24 on
Language Modelling
on Penn Treebank (Word Level)
Been There, Done That: Meta-Learning with Episodic Recall
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins.
Fast deep reinforcement learning using online adjustments from the past
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer.
Infinitely Deep Infinite-Width Networks
Infinite-width neural networks have been extensively used to study the theoretical properties underlying the extraordinary empirical success of standard, finite-width neural networks.
Neural Execution of Graph Algorithms
Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs.
Generalization of Reinforcement Learners with Working and Episodic Memory
In this paper, we aim to develop a comprehensive methodology to test different kinds of memory in an agent and assess how well the agent can apply what it learns in training to a holdout set that differs from the training set along dimensions that we suggest are relevant for evaluating memory-specific generalization.
Shaping representations through communication: community size effect in artificial learning systems
Motivated by theories of language and communication that explain why communities with large numbers of speakers have, on average, simpler languages with more regularity, we cast the representation learning problem in terms of learning to communicate.
MEMO: A Deep Network for Flexible Combination of Episodic Memories
First, it introduces a separation between memories (facts) stored in external memory and the items that comprise these facts in external memory.
Targeted free energy estimation via learned mappings
Here, we cast Targeted FEP as a machine learning problem in which the mapping is parameterized as a neural network that is optimized so as to increase overlap.
Never Give Up: Learning Directed Exploration Strategies
Our method doubles the performance of the base agent in all hard exploration in the Atari-57 suite while maintaining a very high score across the remaining games, obtaining a median human normalised score of 1344. 0%.
Ranked #7 on
Atari Games
on atari game
Agent57: Outperforming the Atari Human Benchmark
Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade.
Ranked #1 on
Atari Games
on Atari 2600 HERO
Pointer Graph Networks
This static input structure is often informed purely by insight of the machine learning practitioner, and might not be optimal for the actual task the GNN is solving.
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
To use a video game as an illustration, two enemies of the same type will share schemata but will have separate object files to encode their distinct state (e. g., health, position).
Representation Learning via Invariant Causal Mechanisms
Self-supervised learning has emerged as a strategy to reduce the reliance on costly supervised signal by pretraining representations only using unlabeled data.
Ranked #77 on
Self-Supervised Image Classification
on ImageNet
Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments
To use a video game as an illustration, two enemies of the same type will share schemata but will have separate object files to encode their distinct state (e. g., health, position).
Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning
We introduce Behavior Transfer (BT), a technique that leverages pre-trained policies for exploration and that is complementary to transferring neural network weights.
Coordination Among Neural Modules Through a Shared Global Workspace
We explore the use of such a communication channel in the context of deep learning for modeling the structure of complex environments.
Persistent Message Passing
Graph neural networks (GNNs) are a powerful inductive bias for modelling algorithmic reasoning procedures and data structures.
Neural Production Systems: Learning Rule-Governed Visual Dynamics
First, GNNs do not predispose interactions to be sparse, as relationships among independent entities are likely to be.
Neural Algorithmic Reasoning
Algorithms have been fundamental to recent global technological advances and, in particular, they have been the cornerstone of technical advances in one field rapidly being applied to another.
Emphatic Algorithms for Deep Reinforcement Learning
In this paper, we extend the use of emphatic methods to deep reinforcement learning agents.
CoBERL: Contrastive BERT for Reinforcement Learning
Many reinforcement learning (RL) agents require a large amount of experience to solve tasks.
PonderNet: Learning to Ponder
In standard neural networks the amount of computation used grows with the size of the inputs, but not with the complexity of the problem being learnt.
Reasoning-Modulated Representations
Neural networks leverage robust internal representations in order to generalise.
Normalizing flows for atomic solids
We present a machine-learning approach, based on normalizing flows, for modelling atomic solids.
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Most notably, ReLICv2 is the first unsupervised representation learning method to consistently outperform the supervised baseline in a like-for-like comparison over a range of ResNet architectures.
Ranked #14 on
Semantic Segmentation
on PASCAL VOC 2012 val
Representation Learning
Self-Supervised Image Classification
+3
Retrieval-Augmented Reinforcement Learning
In this paper we explore an alternative paradigm in which we train a network to map a dataset of past experiences to optimal behavior.
The CLRS Algorithmic Reasoning Benchmark
Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms.
Human-level Atari 200x faster
The task of building general agents that perform well over a wide range of tasks has been an importantgoal in reinforcement learning since its inception.
A Generalist Neural Algorithmic Learner
The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution.
SemPPL: Predicting pseudo-labels for better contrastive representations
We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that combines labelled and unlabelled data to learn informative representations.
Neural Algorithmic Reasoning with Causal Regularisation
We evaluate our method on the CLRS algorithmic reasoning benchmark, where we show up to 3$\times$ improvements on the OOD test data.
Unlocking the Power of Representations in Long-term Novelty-based Exploration
We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for clusters of states based on their similarity in a chosen embedding space.
Improving fine-grained understanding in image-text pre-training
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs.
Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs).
