2 code implementations • 6 Jun 2024 • Larisa Markeeva, Sean McLeish, Borja Ibarz, Wilfried Bounsi, Olga Kozlova, Alex Vitvitskyi, Charles Blundell, Tom Goldstein, Avi Schwarzschild, Petar Veličković
Three years ago, a similar issue was identified and rectified in the field of neural algorithmic reasoning, with the advent of the CLRS benchmark.
no code implementations • 12 Mar 2024 • Sahand Sharifzadeh, Christos Kaplanis, Shreya Pathak, Dharshan Kumaran, Anastasija Ilic, Jovana Mitrovic, Charles Blundell, Andrea Banino
Despite the text-to-image model and VLM initially being trained on the same data, our approach leverages the image generator's ability to create novel compositions, resulting in synthetic image embeddings that expand beyond the limitations of the original dataset.
no code implementations • 18 Jan 2024 • Ioana Bica, Anastasija Ilić, Matthias Bauer, Goker Erdogan, Matko Bošnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrović
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs.
no code implementations • 2 May 2023 • Alaa Saade, Steven Kapturowski, Daniele Calandriello, Charles Blundell, Pablo Sprechmann, Leopoldo Sarra, Oliver Groth, Michal Valko, Bilal Piot
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.
no code implementations • 20 Feb 2023 • Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković
We evaluate our method on the CLRS algorithmic reasoning benchmark, where we show up to 3$\times$ improvements on the OOD test data.
2 code implementations • 12 Jan 2023 • Matko Bošnjak, Pierre H. Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that combines labelled and unlabelled data to learn informative representations.
2 code implementations • 22 Sep 2022 • Borja Ibarz, Vitaly Kurin, George Papamakarios, Kyriacos Nikiforou, Mehdi Bennani, Róbert Csordás, Andrew Dudzik, Matko Bošnjak, Alex Vitvitskyi, Yulia Rubanova, Andreea Deac, Beatrice Bevilacqua, Yaroslav Ganin, Charles Blundell, Petar Veličković
The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution.
1 code implementation • 15 Sep 2022 • Steven Kapturowski, Víctor Campos, Ray Jiang, Nemanja Rakićević, Hado van Hasselt, Charles Blundell, Adrià Puigdomènech Badia
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.
1 code implementation • 31 May 2022 • Petar Veličković, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell
Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms.
no code implementations • 17 Feb 2022 • Anirudh Goyal, Abram L. Friesen, Andrea Banino, Theophane Weber, Nan Rosemary Ke, Adria Puigdomenech Badia, Arthur Guez, Mehdi Mirza, Peter C. Humphreys, Ksenia Konyushkova, Laurent SIfre, Michal Valko, Simon Osindero, Timothy Lillicrap, Nicolas Heess, Charles Blundell
In this paper we explore an alternative paradigm in which we train a network to map a dataset of past experiences to optimal behavior.
1 code implementation • 13 Jan 2022 • Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
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
1 code implementation • 16 Nov 2021 • Peter Wirnsberger, George Papamakarios, Borja Ibarz, Sébastien Racanière, Andrew J. Ballard, Alexander Pritzel, Charles Blundell
We present a machine-learning approach, based on normalizing flows, for modelling atomic solids.
no code implementations • 19 Jul 2021 • Petar Veličković, Matko Bošnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell
Neural networks leverage robust internal representations in order to generalise.
4 code implementations • ICML Workshop AutoML 2021 • Andrea Banino, Jan Balaguer, Charles Blundell
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.
2 code implementations • ICML Workshop URL 2021 • Andrea Banino, Adrià Puidomenech Badia, Jacob Walker, Tim Scholtes, Jovana Mitrovic, Charles Blundell
Many reinforcement learning (RL) agents require a large amount of experience to solve tasks.
no code implementations • 21 Jun 2021 • Ray Jiang, Tom Zahavy, Zhongwen Xu, Adam White, Matteo Hessel, Charles Blundell, Hado van Hasselt
In this paper, we extend the use of emphatic methods to deep reinforcement learning agents.
no code implementations • 6 May 2021 • Petar Veličković, Charles Blundell
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.
no code implementations • NeurIPS 2021 • Anirudh Goyal, Aniket Didolkar, Nan Rosemary Ke, Charles Blundell, Philippe Beaudoin, Nicolas Heess, Michael Mozer, Yoshua Bengio
First, GNNs do not predispose interactions to be sparse, as relationships among independent entities are likely to be.
no code implementations • ICLR Workshop GTRL 2021 • Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell, Petar Veličković
Graph neural networks (GNNs) are a powerful inductive bias for modelling algorithmic reasoning procedures and data structures.
1 code implementation • ICLR 2022 • Anirudh Goyal, Aniket Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke, Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Mozer, Yoshua Bengio
We explore the use of such a communication channel in the context of deep learning for modeling the structure of complex environments.
no code implementations • 24 Feb 2021 • Víctor Campos, Pablo Sprechmann, Steven Hansen, Andre Barreto, Steven Kapturowski, Alex Vitvitskyi, Adrià Puigdomènech Badia, Charles Blundell
We introduce Behavior Transfer (BT), a technique that leverages pre-trained policies for exploration and that is complementary to transferring neural network weights.
no code implementations • ICLR 2021 • Anirudh Goyal, Alex Lamb, Phanideep Gampa, Philippe Beaudoin, Charles Blundell, Sergey Levine, Yoshua Bengio, Michael Curtis Mozer
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).
2 code implementations • 15 Oct 2020 • Jovana Mitrovic, Brian McWilliams, Jacob Walker, Lars Buesing, Charles Blundell
Self-supervised learning has emerged as a strategy to reduce the reliance on costly supervised signal by pretraining representations only using unlabeled data.
Ranked #79 on
Self-Supervised Image Classification
on ImageNet
no code implementations • 29 Jun 2020 • Anirudh Goyal, Alex Lamb, Phanideep Gampa, Philippe Beaudoin, Sergey Levine, Charles Blundell, Yoshua Bengio, Michael Mozer
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).
no code implementations • NeurIPS 2020 • Petar Veličković, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell
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.
5 code implementations • ICML 2020 • Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Charles Blundell
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
6 code implementations • ICLR 2020 • Adrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Bilal Piot, Steven Kapturowski, Olivier Tieleman, Martín Arjovsky, Alexander Pritzel, Andew Bolt, Charles Blundell
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
no code implementations • 12 Feb 2020 • Peter Wirnsberger, Andrew J. Ballard, George Papamakarios, Stuart Abercrombie, Sébastien Racanière, Alexander Pritzel, Danilo Jimenez Rezende, Charles Blundell
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.
no code implementations • ICLR 2020 • Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinicius Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, Charles Blundell
First, it introduces a separation between memories (facts) stored in external memory and the items that comprise these facts in external memory.
no code implementations • 12 Dec 2019 • Olivier Tieleman, Angeliki Lazaridou, Shibl Mourad, Charles Blundell, Doina Precup
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.
1 code implementation • NeurIPS 2019 • Meire Fortunato, Melissa Tan, Ryan Faulkner, Steven Hansen, Adrià Puigdomènech Badia, Gavin Buttimore, Charlie Deck, Joel Z. Leibo, Charles Blundell
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.
no code implementations • ICLR 2020 • Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell
Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs.
no code implementations • ICLR 2019 • Jovana Mitrovic, Peter Wirnsberger, Charles Blundell, Dino Sejdinovic, Yee Whye Teh
Infinite-width neural networks have been extensively used to study the theoretical properties underlying the extraordinary empirical success of standard, finite-width neural networks.
2 code implementations • NeurIPS 2018 • Steven Hansen, Pablo Sprechmann, Alexander Pritzel, André Barreto, Charles Blundell
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer.
1 code implementation • ICML 2018 • Samuel Ritter, Jane. X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew Botvinick
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.
1 code implementation • ICLR 2019 • Gábor Melis, Charles Blundell, Tomáš Kočiský, Karl Moritz Hermann, Chris Dyer, Phil Blunsom
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)
no code implementations • ICLR 2018 • Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell
Deep neural networks have excelled on a wide range of problems, from vision to language and game playing.
no code implementations • ICLR 2018 • Meire Fortunato, Charles Blundell, Oriol Vinyals
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.
1 code implementation • ICML 2017 • Irina Higgins, Arka Pal, Andrei A. Rusu, Loic Matthey, Christopher P. Burgess, Alexander Pritzel, Matthew Botvinick, Charles Blundell, Alexander Lerchner
Domain adaptation is an important open problem in deep reinforcement learning (RL).
15 code implementations • ICLR 2018 • Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg
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
4 code implementations • 10 Apr 2017 • Meire Fortunato, Charles Blundell, Oriol Vinyals
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.
4 code implementations • ICML 2017 • Alexander Pritzel, Benigno Uria, Sriram Srinivasan, Adrià Puigdomènech, Oriol Vinyals, Demis Hassabis, Daan Wierstra, Charles Blundell
Deep reinforcement learning methods attain super-human performance in a wide range of environments.
1 code implementation • 28 Feb 2017 • Daniel Zoran, Balaji Lakshminarayanan, Charles Blundell
We introduce a new method called differentiable boundary tree which allows for learning deep kNN representations.
1 code implementation • 30 Jan 2017 • Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, Daan Wierstra
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)
27 code implementations • NeurIPS 2017 • Balaji Lakshminarayanan, Alexander Pritzel, Charles Blundell
Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks.
9 code implementations • 17 Nov 2016 • Jane. X. Wang, Zeb Kurth-Nelson, Dhruva Tirumala, Hubert Soyer, Joel Z. Leibo, Remi Munos, Charles Blundell, Dharshan Kumaran, Matt Botvinick
We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.
1 code implementation • 17 Jun 2016 • Irina Higgins, Loic Matthey, Xavier Glorot, Arka Pal, Benigno Uria, Charles Blundell, Shakir Mohamed, Alexander Lerchner
Automated discovery of early visual concepts from raw image data is a major open challenge in AI research.
3 code implementations • 14 Jun 2016 • Charles Blundell, Benigno Uria, Alexander Pritzel, Yazhe Li, Avraham Ruderman, Joel Z. Leibo, Jack Rae, Daan Wierstra, Demis Hassabis
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance.
26 code implementations • NeurIPS 2016 • Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra
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.
6 code implementations • NeurIPS 2016 • Ian Osband, Charles Blundell, Alexander Pritzel, Benjamin Van Roy
Efficient exploration in complex environments remains a major challenge for reinforcement learning.
Ranked #5 on
Atari Games
on Atari 2600 Breakout
no code implementations • 31 Dec 2015 • Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer, Balaji Lakshminarayanan, Charles Blundell, Yee Whye Teh
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.
37 code implementations • 20 May 2015 • Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra
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.
no code implementations • 11 Nov 2014 • Fangjian Guo, Charles Blundell, Hanna Wallach, Katherine Heller
We present the Bayesian Echo Chamber, a new Bayesian generative model for social interaction data.
no code implementations • NeurIPS 2013 • Charles Blundell, Yee Whye Teh
We propose an efficient Bayesian nonparametric model for discovering hierarchical community structure in social networks.
no code implementations • 31 Oct 2013 • Karol Gregor, Ivo Danihelka, andriy mnih, Charles Blundell, Daan Wierstra
We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data.
no code implementations • NeurIPS 2012 • Charles Blundell, Jeff Beck, Katherine A. Heller
We present a Bayesian nonparametric model that discovers implicit social structure from interaction time-series data.
no code implementations • NeurIPS 2011 • Yee W. Teh, Charles Blundell, Lloyd Elliott
We propose a novel class of Bayesian nonparametric models for sequential data called fragmentation-coagulation processes (FCPs).