no code implementations • 26 Jul 2024 • Misha Denil
In this report we consider the problem of rapidly annotating a video with bounding boxes for a novel object.
no code implementations • 20 Jun 2023 • Konstantinos Bousmalis, Giulia Vezzani, Dushyant Rao, Coline Devin, Alex X. Lee, Maria Bauza, Todor Davchev, Yuxiang Zhou, Agrim Gupta, Akhil Raju, Antoine Laurens, Claudio Fantacci, Valentin Dalibard, Martina Zambelli, Murilo Martins, Rugile Pevceviciute, Michiel Blokzijl, Misha Denil, Nathan Batchelor, Thomas Lampe, Emilio Parisotto, Konrad Żołna, Scott Reed, Sergio Gómez Colmenarejo, Jon Scholz, Abbas Abdolmaleki, Oliver Groth, Jean-Baptiste Regli, Oleg Sushkov, Tom Rothörl, José Enrique Chen, Yusuf Aytar, Dave Barker, Joy Ortiz, Martin Riedmiller, Jost Tobias Springenberg, Raia Hadsell, Francesco Nori, Nicolas Heess
With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task.
no code implementations • 16 Jun 2023 • Gianluca Scarpellini, Ksenia Konyushkova, Claudio Fantacci, Tom Le Paine, Yutian Chen, Misha Denil
This paper describes $\pi2\text{vec}$, a method for representing behaviors of black box policies as feature vectors.
no code implementations • 13 Mar 2023 • Yuqing Du, Ksenia Konyushkova, Misha Denil, Akhil Raju, Jessica Landon, Felix Hill, Nando de Freitas, Serkan Cabi
Detecting successful behaviour is crucial for training intelligent agents.
no code implementations • 1 Jul 2021 • Brendan Shillingford, Yannis Assael, Misha Denil
This work describes an interactive decoding method to improve the performance of visual speech recognition systems using user input to compensate for the inherent ambiguity of the task.
1 code implementation • NeurIPS 2021 • Ksenia Konyushkova, Yutian Chen, Tom Le Paine, Caglar Gulcehre, Cosmin Paduraru, Daniel J Mankowitz, Misha Denil, Nando de Freitas
We use multiple benchmarks, including real-world robotics, with a large number of candidate policies to show that the proposed approach improves upon state-of-the-art OPE estimates and pure online policy evaluation.
no code implementations • 27 Nov 2020 • Konrad Zolna, Alexander Novikov, Ksenia Konyushkova, Caglar Gulcehre, Ziyu Wang, Yusuf Aytar, Misha Denil, Nando de Freitas, Scott Reed
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.
no code implementations • 6 Nov 2020 • Yi Yang, Brendan Shillingford, Yannis Assael, Miaosen Wang, Wendi Liu, Yutian Chen, Yu Zhang, Eren Sezener, Luis C. Cobo, Misha Denil, Yusuf Aytar, Nando de Freitas
The visual content is translated by synthesizing lip movements for the speaker to match the translated audio, creating a seamless audiovisual experience in the target language.
1 code implementation • 1 Nov 2019 • Danfei Xu, Misha Denil
Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics.
no code implementations • 2 Oct 2019 • Konrad Zolna, Scott Reed, Alexander Novikov, Sergio Gomez Colmenarejo, David Budden, Serkan Cabi, Misha Denil, Nando de Freitas, Ziyu Wang
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels.
1 code implementation • 26 Sep 2019 • Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott Reed, Rae Jeong, Konrad Zolna, Yusuf Aytar, David Budden, Mel Vecerik, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
1 code implementation • ICLR 2020 • Tom Le Paine, Caglar Gulcehre, Bobak Shahriari, Misha Denil, Matt Hoffman, Hubert Soyer, Richard Tanburn, Steven Kapturowski, Neil Rabinowitz, Duncan Williams, Gabriel Barth-Maron, Ziyu Wang, Nando de Freitas, Worlds Team
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions.
no code implementations • ICLR 2019 • Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas
We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.
no code implementations • ICLR 2018 • Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo, Alistair Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, Misha Denil
We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world.
no code implementations • 11 Jul 2017 • Serkan Cabi, Sergio Gómez Colmenarejo, Matthew W. Hoffman, Misha Denil, Ziyu Wang, Nando de Freitas
This paper introduces the Intentional Unintentional (IU) agent.
no code implementations • 20 Jun 2017 • Misha Denil, Sergio Gómez Colmenarejo, Serkan Cabi, David Saxton, Nando de Freitas
We build deep RL agents that execute declarative programs expressed in formal language.
1 code implementation • ICML 2017 • Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein
Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks.
1 code implementation • 11 Nov 2016 • Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J. Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent SIfre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell
Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents.
no code implementations • ICML 2017 • Yutian Chen, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Timothy P. Lillicrap, Matt Botvinick, Nando de Freitas
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent.
no code implementations • 6 Nov 2016 • Misha Denil, Pulkit Agrawal, Tejas D. Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas
When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way.
8 code implementations • NeurIPS 2016 • Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas
The move from hand-designed features to learned features in machine learning has been wildly successful.
1 code implementation • 1 Mar 2016 • Caglar Gulcehre, Marcin Moczulski, Misha Denil, Yoshua Bengio
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only).
2 code implementations • 18 Nov 2015 • Marcin Moczulski, Misha Denil, Jeremy Appleyard, Nando de Freitas
Finally, this paper also provides a connection between structured linear transforms used in deep learning and the field of Fourier optics, illustrating how ACDC could in principle be implemented with lenses and diffractive elements.
1 code implementation • ICCV 2015 • Zichao Yang, Marcin Moczulski, Misha Denil, Nando de Freitas, Alex Smola, Le Song, Ziyu Wang
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters.
Ranked #44 on
Image Classification
on MNIST
2 code implementations • 21 Dec 2014 • Misha Denil, Alban Demiraj, Nando de Freitas
We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure.
no code implementations • 12 Nov 2014 • Dimitrios Kotzias, Misha Denil, Phil Blunsom, Nando de Freitas
We present a new approach for transferring knowledge from groups to individuals that comprise them.
no code implementations • 15 Jun 2014 • Misha Denil, Alban Demiraj, Nal Kalchbrenner, Phil Blunsom, Nando de Freitas
Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval.
no code implementations • NeurIPS 2014 • Yariv Dror Mizrahi, Misha Denil, Nando de Freitas
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models.
no code implementations • 4 Oct 2013 • Misha Denil, David Matheson, Nando de Freitas
Despite widespread interest and practical use, the theoretical properties of random forests are still not well understood.
no code implementations • 29 Aug 2013 • Yariv Dror Mizrahi, Misha Denil, Nando de Freitas
We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields with untied parameters which is efficient for a large class of practical models.
no code implementations • NeurIPS 2013 • Misha Denil, Babak Shakibi, Laurent Dinh, Marc'Aurelio Ranzato, Nando de Freitas
We demonstrate that there is significant redundancy in the parameterization of several deep learning models.
1 code implementation • 20 Feb 2013 • Misha Denil, David Matheson, Nando de Freitas
As a testament to their success, the theory of random forests has long been outpaced by their application in practice.